2023/02/17 23:08:20 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.7.0 (default, Oct 9 2018, 10:31:47) [GCC 7.3.0] CUDA available: True numpy_random_seed: 1918948137 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/cache/share/cuda-11.1 NVCC: Cuda compilation tools, release 11.1, V11.1.74 GCC: gcc (GCC) 5.4.0 PyTorch: 1.9.0+cu111 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86 - CuDNN 8.0.5 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.9.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, TorchVision: 0.10.0+cu111 OpenCV: 4.6.0 MMEngine: 0.5.0 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None diff_rank_seed: False deterministic: False Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2023/02/17 23:08:20 - mmengine - INFO - Config: preprocess_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]) model = dict( type='Recognizer2D', backbone=dict( type='ResNetTSM', pretrained='torchvision://resnet50', depth=50, norm_eval=False, shift_div=8), cls_head=dict( type='TSMHead', num_classes=174, in_channels=2048, spatial_type='avg', consensus=dict(type='AvgConsensus', dim=1), dropout_ratio=0.5, init_std=0.001, is_shift=True, average_clips='prob'), data_preprocessor=dict( type='ActionDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]), train_cfg=None, test_cfg=None) default_scope = 'mmaction' default_hooks = dict( runtime_info=dict(type='RuntimeInfoHook'), timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=20, ignore_last=False), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict( type='CheckpointHook', interval=3, save_best='auto', max_keep_ckpts=3), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffers=dict(type='SyncBuffersHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) log_processor = dict(type='LogProcessor', window_size=20, by_epoch=True) vis_backends = [ dict(type='LocalVisBackend'), dict(type='TensorboardVisBackend') ] visualizer = dict( type='ActionVisualizer', vis_backends=[ dict(type='LocalVisBackend'), dict(type='TensorboardVisBackend') ]) log_level = 'INFO' load_from = None resume = False dataset_type = 'VideoDataset' data_root = 'data/sthv2/videos' ann_file_train = 'data/sthv2/sthv2_train_list_videos.txt' ann_file_val = 'data/sthv2/sthv2_val_list_videos.txt' file_client_args = dict( io_backend='petrel', path_mapping=dict( {'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2'})) sthv2_flip_label_map = dict({ 86: 87, 87: 86, 93: 94, 94: 93, 166: 167, 167: 166 }) train_pipeline = [ dict( type='DecordInit', io_backend='petrel', path_mapping=dict( {'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2'})), dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict( type='MultiScaleCrop', input_size=224, scales=(1, 0.875, 0.75, 0.66), random_crop=False, max_wh_scale_gap=1, num_fixed_crops=13), dict(type='Resize', scale=(224, 224), keep_ratio=False), dict( type='Flip', flip_ratio=0.5, flip_label_map=dict({ 86: 87, 87: 86, 93: 94, 94: 93, 166: 167, 167: 166 })), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ] val_pipeline = [ dict( type='DecordInit', io_backend='petrel', path_mapping=dict( {'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2'})), dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8, test_mode=True), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=224), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ] test_pipeline = [ dict( type='DecordInit', io_backend='petrel', path_mapping=dict( {'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2'})), dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8, test_mode=True, twice_sample=True), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='TenCrop', crop_size=224), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=8, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='VideoDataset', ann_file='data/sthv2/sthv2_train_list_videos.txt', data_prefix=dict(video='data/sthv2/videos'), pipeline=[ dict( type='DecordInit', io_backend='petrel', path_mapping=dict({ 'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2' })), dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict( type='MultiScaleCrop', input_size=224, scales=(1, 0.875, 0.75, 0.66), random_crop=False, max_wh_scale_gap=1, num_fixed_crops=13), dict(type='Resize', scale=(224, 224), keep_ratio=False), dict( type='Flip', flip_ratio=0.5, flip_label_map=dict({ 86: 87, 87: 86, 93: 94, 94: 93, 166: 167, 167: 166 })), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ])) val_dataloader = dict( batch_size=16, num_workers=8, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='VideoDataset', ann_file='data/sthv2/sthv2_val_list_videos.txt', data_prefix=dict(video='data/sthv2/videos'), pipeline=[ dict( type='DecordInit', io_backend='petrel', path_mapping=dict({ 'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2' })), dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8, test_mode=True), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=224), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ], test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=8, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='VideoDataset', ann_file='data/sthv2/sthv2_val_list_videos.txt', data_prefix=dict(video='data/sthv2/videos'), pipeline=[ dict( type='DecordInit', io_backend='petrel', path_mapping=dict({ 'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2' })), dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8, test_mode=True, twice_sample=True), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='TenCrop', crop_size=224), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ], test_mode=True)) val_evaluator = dict(type='AccMetric') test_evaluator = dict(type='AccMetric') train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=50, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict(type='LinearLR', start_factor=0.1, by_epoch=True, begin=0, end=5), dict( type='MultiStepLR', begin=0, end=50, by_epoch=True, milestones=[25, 45], gamma=0.1) ] optim_wrapper = dict( constructor='TSMOptimWrapperConstructor', paramwise_cfg=dict(fc_lr5=True), optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0005), clip_grad=dict(max_norm=20, norm_type=2)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = 'work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2023/02/17 23:08:23 - mmengine - INFO - These parameters in pretrained checkpoint are not loaded: {'fc.bias', 'fc.weight'} 2023/02/17 23:08:23 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (BELOW_NORMAL) LoggerHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) SyncBuffersHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- Name of parameter - Initialization information backbone.conv1.conv.weight - torch.Size([64, 3, 7, 7]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.conv1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.conv1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv1.conv.net.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv2.conv.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv3.conv.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.downsample.conv.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.downsample.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.downsample.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv1.conv.net.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv2.conv.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv3.conv.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv1.conv.net.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv2.conv.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv3.conv.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv1.conv.net.weight - torch.Size([128, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv2.conv.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv3.conv.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.downsample.conv.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.downsample.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.downsample.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv1.conv.net.weight - torch.Size([128, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv2.conv.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv3.conv.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv1.conv.net.weight - torch.Size([128, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv2.conv.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv3.conv.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv1.conv.net.weight - torch.Size([128, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv2.conv.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv3.conv.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv1.conv.net.weight - torch.Size([256, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.downsample.conv.weight - torch.Size([1024, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.downsample.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.downsample.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv1.conv.net.weight - torch.Size([256, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv1.conv.net.weight - torch.Size([256, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv1.conv.net.weight - torch.Size([256, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv1.conv.net.weight - torch.Size([256, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv1.conv.net.weight - torch.Size([256, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv1.conv.net.weight - torch.Size([512, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv2.conv.weight - torch.Size([512, 512, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv3.conv.weight - torch.Size([2048, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv3.bn.weight - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv3.bn.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.downsample.conv.weight - torch.Size([2048, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.downsample.bn.weight - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.downsample.bn.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv1.conv.net.weight - torch.Size([512, 2048, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv2.conv.weight - torch.Size([512, 512, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv3.conv.weight - torch.Size([2048, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv3.bn.weight - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv3.bn.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv1.conv.net.weight - torch.Size([512, 2048, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv2.conv.weight - torch.Size([512, 512, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv3.conv.weight - torch.Size([2048, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv3.bn.weight - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv3.bn.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D cls_head.fc_cls.weight - torch.Size([174, 2048]): Initialized by user-defined `init_weights` in TSMHead cls_head.fc_cls.bias - torch.Size([174]): Initialized by user-defined `init_weights` in TSMHead 2023/02/17 23:08:25 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py. 2023/02/17 23:09:13 - mmengine - INFO - Epoch(train) [1][ 20/1320] lr: 2.0000e-03 eta: 1 day, 19:22:29 time: 2.3666 data_time: 2.0925 memory: 13708 grad_norm: 2.4386 loss: 5.0457 top1_acc: 0.0625 top5_acc: 0.0625 loss_cls: 5.0457 2023/02/17 23:09:18 - mmengine - INFO - Epoch(train) [1][ 40/1320] lr: 2.0000e-03 eta: 1 day, 0:01:09 time: 0.2552 data_time: 0.0102 memory: 13708 grad_norm: 2.4523 loss: 5.0264 top1_acc: 0.0000 top5_acc: 0.1250 loss_cls: 5.0264 2023/02/17 23:09:23 - mmengine - INFO - Epoch(train) [1][ 60/1320] lr: 2.0000e-03 eta: 17:33:53 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 2.5346 loss: 4.8339 top1_acc: 0.0625 top5_acc: 0.0625 loss_cls: 4.8339 2023/02/17 23:09:28 - mmengine - INFO - Epoch(train) [1][ 80/1320] lr: 2.0000e-03 eta: 14:20:30 time: 0.2560 data_time: 0.0119 memory: 13708 grad_norm: 2.5892 loss: 4.9352 top1_acc: 0.1250 top5_acc: 0.1875 loss_cls: 4.9352 2023/02/17 23:09:33 - mmengine - INFO - Epoch(train) [1][ 100/1320] lr: 2.0000e-03 eta: 12:24:15 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 2.6706 loss: 4.7878 top1_acc: 0.0625 top5_acc: 0.0625 loss_cls: 4.7878 2023/02/17 23:09:38 - mmengine - INFO - Epoch(train) [1][ 120/1320] lr: 2.0000e-03 eta: 11:06:46 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 2.8540 loss: 4.8145 top1_acc: 0.0625 top5_acc: 0.0625 loss_cls: 4.8145 2023/02/17 23:09:44 - mmengine - INFO - Epoch(train) [1][ 140/1320] lr: 2.0000e-03 eta: 10:14:28 time: 0.2750 data_time: 0.0306 memory: 13708 grad_norm: 2.9427 loss: 4.7103 top1_acc: 0.0000 top5_acc: 0.1250 loss_cls: 4.7103 2023/02/17 23:09:49 - mmengine - INFO - Epoch(train) [1][ 160/1320] lr: 2.0000e-03 eta: 9:32:28 time: 0.2550 data_time: 0.0102 memory: 13708 grad_norm: 2.9885 loss: 4.5290 top1_acc: 0.0000 top5_acc: 0.2500 loss_cls: 4.5290 2023/02/17 23:09:54 - mmengine - INFO - Epoch(train) [1][ 180/1320] lr: 2.0000e-03 eta: 8:59:52 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 3.1408 loss: 4.6429 top1_acc: 0.0625 top5_acc: 0.3750 loss_cls: 4.6429 2023/02/17 23:09:59 - mmengine - INFO - Epoch(train) [1][ 200/1320] lr: 2.0000e-03 eta: 8:33:47 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 3.1318 loss: 4.5897 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 4.5897 2023/02/17 23:10:04 - mmengine - INFO - Epoch(train) [1][ 220/1320] lr: 2.0000e-03 eta: 8:12:33 time: 0.2569 data_time: 0.0121 memory: 13708 grad_norm: 3.2800 loss: 4.6022 top1_acc: 0.0000 top5_acc: 0.1250 loss_cls: 4.6022 2023/02/17 23:10:09 - mmengine - INFO - Epoch(train) [1][ 240/1320] lr: 2.0000e-03 eta: 7:54:39 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 3.2880 loss: 4.4257 top1_acc: 0.0625 top5_acc: 0.1875 loss_cls: 4.4257 2023/02/17 23:10:14 - mmengine - INFO - Epoch(train) [1][ 260/1320] lr: 2.0000e-03 eta: 7:39:39 time: 0.2569 data_time: 0.0108 memory: 13708 grad_norm: 3.4090 loss: 4.3728 top1_acc: 0.0625 top5_acc: 0.3125 loss_cls: 4.3728 2023/02/17 23:10:19 - mmengine - INFO - Epoch(train) [1][ 280/1320] lr: 2.0000e-03 eta: 7:26:39 time: 0.2552 data_time: 0.0100 memory: 13708 grad_norm: 3.4788 loss: 4.4568 top1_acc: 0.1250 top5_acc: 0.3125 loss_cls: 4.4568 2023/02/17 23:10:24 - mmengine - INFO - Epoch(train) [1][ 300/1320] lr: 2.0000e-03 eta: 7:15:21 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 3.5410 loss: 4.4402 top1_acc: 0.0000 top5_acc: 0.1875 loss_cls: 4.4402 2023/02/17 23:10:30 - mmengine - INFO - Epoch(train) [1][ 320/1320] lr: 2.0000e-03 eta: 7:05:26 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 3.6294 loss: 4.3877 top1_acc: 0.0625 top5_acc: 0.1250 loss_cls: 4.3877 2023/02/17 23:10:35 - mmengine - INFO - Epoch(train) [1][ 340/1320] lr: 2.0000e-03 eta: 6:56:40 time: 0.2545 data_time: 0.0101 memory: 13708 grad_norm: 3.7476 loss: 4.3878 top1_acc: 0.0000 top5_acc: 0.3750 loss_cls: 4.3878 2023/02/17 23:10:40 - mmengine - INFO - Epoch(train) [1][ 360/1320] lr: 2.0000e-03 eta: 6:48:54 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 3.7782 loss: 4.3237 top1_acc: 0.0000 top5_acc: 0.1250 loss_cls: 4.3237 2023/02/17 23:10:45 - mmengine - INFO - Epoch(train) [1][ 380/1320] lr: 2.0000e-03 eta: 6:41:58 time: 0.2555 data_time: 0.0112 memory: 13708 grad_norm: 3.7990 loss: 4.2697 top1_acc: 0.0000 top5_acc: 0.1875 loss_cls: 4.2697 2023/02/17 23:10:50 - mmengine - INFO - Epoch(train) [1][ 400/1320] lr: 2.0000e-03 eta: 6:35:42 time: 0.2550 data_time: 0.0111 memory: 13708 grad_norm: 3.8563 loss: 4.3309 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 4.3309 2023/02/17 23:10:55 - mmengine - INFO - Epoch(train) [1][ 420/1320] lr: 2.0000e-03 eta: 6:30:01 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 3.8916 loss: 4.2375 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 4.2375 2023/02/17 23:11:00 - mmengine - INFO - Epoch(train) [1][ 440/1320] lr: 2.0000e-03 eta: 6:24:49 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 3.9183 loss: 4.3027 top1_acc: 0.0625 top5_acc: 0.1875 loss_cls: 4.3027 2023/02/17 23:11:05 - mmengine - INFO - Epoch(train) [1][ 460/1320] lr: 2.0000e-03 eta: 6:20:05 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.0271 loss: 4.0834 top1_acc: 0.0000 top5_acc: 0.1250 loss_cls: 4.0834 2023/02/17 23:11:10 - mmengine - INFO - Epoch(train) [1][ 480/1320] lr: 2.0000e-03 eta: 6:15:45 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.1335 loss: 4.2592 top1_acc: 0.1250 top5_acc: 0.1875 loss_cls: 4.2592 2023/02/17 23:11:15 - mmengine - INFO - Epoch(train) [1][ 500/1320] lr: 2.0000e-03 eta: 6:11:45 time: 0.2552 data_time: 0.0103 memory: 13708 grad_norm: 4.1695 loss: 4.1484 top1_acc: 0.1250 top5_acc: 0.2500 loss_cls: 4.1484 2023/02/17 23:11:21 - mmengine - INFO - Epoch(train) [1][ 520/1320] lr: 2.0000e-03 eta: 6:08:03 time: 0.2552 data_time: 0.0105 memory: 13708 grad_norm: 4.1278 loss: 4.1477 top1_acc: 0.2500 top5_acc: 0.3750 loss_cls: 4.1477 2023/02/17 23:11:26 - mmengine - INFO - Epoch(train) [1][ 540/1320] lr: 2.0000e-03 eta: 6:04:37 time: 0.2549 data_time: 0.0110 memory: 13708 grad_norm: 4.2242 loss: 4.2154 top1_acc: 0.1250 top5_acc: 0.1875 loss_cls: 4.2154 2023/02/17 23:11:31 - mmengine - INFO - Epoch(train) [1][ 560/1320] lr: 2.0000e-03 eta: 6:01:24 time: 0.2545 data_time: 0.0107 memory: 13708 grad_norm: 4.2160 loss: 4.0941 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 4.0941 2023/02/17 23:11:36 - mmengine - INFO - Epoch(train) [1][ 580/1320] lr: 2.0000e-03 eta: 5:58:27 time: 0.2560 data_time: 0.0107 memory: 13708 grad_norm: 4.3594 loss: 4.0515 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 4.0515 2023/02/17 23:11:41 - mmengine - INFO - Epoch(train) [1][ 600/1320] lr: 2.0000e-03 eta: 5:55:40 time: 0.2552 data_time: 0.0113 memory: 13708 grad_norm: 4.3601 loss: 4.0442 top1_acc: 0.1250 top5_acc: 0.2500 loss_cls: 4.0442 2023/02/17 23:11:46 - mmengine - INFO - Epoch(train) [1][ 620/1320] lr: 2.0000e-03 eta: 5:53:04 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.3612 loss: 3.9901 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 3.9901 2023/02/17 23:11:51 - mmengine - INFO - Epoch(train) [1][ 640/1320] lr: 2.0000e-03 eta: 5:50:38 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 4.4001 loss: 3.9282 top1_acc: 0.1250 top5_acc: 0.5000 loss_cls: 3.9282 2023/02/17 23:11:56 - mmengine - INFO - Epoch(train) [1][ 660/1320] lr: 2.0000e-03 eta: 5:48:21 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 4.4014 loss: 4.0360 top1_acc: 0.1250 top5_acc: 0.2500 loss_cls: 4.0360 2023/02/17 23:12:01 - mmengine - INFO - Epoch(train) [1][ 680/1320] lr: 2.0000e-03 eta: 5:46:10 time: 0.2550 data_time: 0.0110 memory: 13708 grad_norm: 4.5330 loss: 4.0203 top1_acc: 0.0625 top5_acc: 0.4375 loss_cls: 4.0203 2023/02/17 23:12:07 - mmengine - INFO - Epoch(train) [1][ 700/1320] lr: 2.0000e-03 eta: 5:44:06 time: 0.2553 data_time: 0.0103 memory: 13708 grad_norm: 4.5928 loss: 4.0794 top1_acc: 0.0625 top5_acc: 0.1875 loss_cls: 4.0794 2023/02/17 23:12:12 - mmengine - INFO - Epoch(train) [1][ 720/1320] lr: 2.0000e-03 eta: 5:42:09 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.6313 loss: 4.0418 top1_acc: 0.0000 top5_acc: 0.5000 loss_cls: 4.0418 2023/02/17 23:12:17 - mmengine - INFO - Epoch(train) [1][ 740/1320] lr: 2.0000e-03 eta: 5:40:20 time: 0.2562 data_time: 0.0115 memory: 13708 grad_norm: 4.7057 loss: 3.9167 top1_acc: 0.0625 top5_acc: 0.1875 loss_cls: 3.9167 2023/02/17 23:12:22 - mmengine - INFO - Epoch(train) [1][ 760/1320] lr: 2.0000e-03 eta: 5:38:35 time: 0.2554 data_time: 0.0113 memory: 13708 grad_norm: 4.7544 loss: 4.1012 top1_acc: 0.0625 top5_acc: 0.4375 loss_cls: 4.1012 2023/02/17 23:12:27 - mmengine - INFO - Epoch(train) [1][ 780/1320] lr: 2.0000e-03 eta: 5:36:55 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 4.6856 loss: 3.8752 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 3.8752 2023/02/17 23:12:32 - mmengine - INFO - Epoch(train) [1][ 800/1320] lr: 2.0000e-03 eta: 5:35:18 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.7672 loss: 3.9026 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 3.9026 2023/02/17 23:12:37 - mmengine - INFO - Epoch(train) [1][ 820/1320] lr: 2.0000e-03 eta: 5:33:47 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 4.7488 loss: 3.9217 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 3.9217 2023/02/17 23:12:42 - mmengine - INFO - Epoch(train) [1][ 840/1320] lr: 2.0000e-03 eta: 5:32:19 time: 0.2549 data_time: 0.0110 memory: 13708 grad_norm: 4.8450 loss: 3.8260 top1_acc: 0.0625 top5_acc: 0.3750 loss_cls: 3.8260 2023/02/17 23:12:48 - mmengine - INFO - Epoch(train) [1][ 860/1320] lr: 2.0000e-03 eta: 5:31:27 time: 0.2754 data_time: 0.0307 memory: 13708 grad_norm: 4.9480 loss: 3.6368 top1_acc: 0.1875 top5_acc: 0.3125 loss_cls: 3.6368 2023/02/17 23:12:53 - mmengine - INFO - Epoch(train) [1][ 880/1320] lr: 2.0000e-03 eta: 5:30:09 time: 0.2570 data_time: 0.0128 memory: 13708 grad_norm: 4.8847 loss: 3.9031 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 3.9031 2023/02/17 23:12:58 - mmengine - INFO - Epoch(train) [1][ 900/1320] lr: 2.0000e-03 eta: 5:28:54 time: 0.2567 data_time: 0.0116 memory: 13708 grad_norm: 4.9559 loss: 3.9832 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 3.9832 2023/02/17 23:13:03 - mmengine - INFO - Epoch(train) [1][ 920/1320] lr: 2.0000e-03 eta: 5:27:44 time: 0.2578 data_time: 0.0140 memory: 13708 grad_norm: 4.9955 loss: 3.8200 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 3.8200 2023/02/17 23:13:08 - mmengine - INFO - Epoch(train) [1][ 940/1320] lr: 2.0000e-03 eta: 5:26:34 time: 0.2559 data_time: 0.0113 memory: 13708 grad_norm: 5.0326 loss: 3.7628 top1_acc: 0.0000 top5_acc: 0.4375 loss_cls: 3.7628 2023/02/17 23:13:13 - mmengine - INFO - Epoch(train) [1][ 960/1320] lr: 2.0000e-03 eta: 5:25:26 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 5.0960 loss: 3.8415 top1_acc: 0.0625 top5_acc: 0.4375 loss_cls: 3.8415 2023/02/17 23:13:19 - mmengine - INFO - Epoch(train) [1][ 980/1320] lr: 2.0000e-03 eta: 5:24:20 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 5.1542 loss: 3.7969 top1_acc: 0.2500 top5_acc: 0.3750 loss_cls: 3.7969 2023/02/17 23:13:24 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:13:24 - mmengine - INFO - Epoch(train) [1][1000/1320] lr: 2.0000e-03 eta: 5:23:17 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 5.0646 loss: 3.6978 top1_acc: 0.1875 top5_acc: 0.3125 loss_cls: 3.6978 2023/02/17 23:13:29 - mmengine - INFO - Epoch(train) [1][1020/1320] lr: 2.0000e-03 eta: 5:22:17 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 5.1591 loss: 3.7771 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 3.7771 2023/02/17 23:13:34 - mmengine - INFO - Epoch(train) [1][1040/1320] lr: 2.0000e-03 eta: 5:21:18 time: 0.2550 data_time: 0.0104 memory: 13708 grad_norm: 5.2433 loss: 3.7974 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.7974 2023/02/17 23:13:39 - mmengine - INFO - Epoch(train) [1][1060/1320] lr: 2.0000e-03 eta: 5:20:22 time: 0.2561 data_time: 0.0114 memory: 13708 grad_norm: 5.1310 loss: 3.7681 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 3.7681 2023/02/17 23:13:44 - mmengine - INFO - Epoch(train) [1][1080/1320] lr: 2.0000e-03 eta: 5:19:27 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 5.1761 loss: 3.6516 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 3.6516 2023/02/17 23:13:49 - mmengine - INFO - Epoch(train) [1][1100/1320] lr: 2.0000e-03 eta: 5:18:34 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 5.3011 loss: 3.8999 top1_acc: 0.1250 top5_acc: 0.2500 loss_cls: 3.8999 2023/02/17 23:13:54 - mmengine - INFO - Epoch(train) [1][1120/1320] lr: 2.0000e-03 eta: 5:17:42 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 5.4154 loss: 3.6353 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.6353 2023/02/17 23:13:59 - mmengine - INFO - Epoch(train) [1][1140/1320] lr: 2.0000e-03 eta: 5:16:53 time: 0.2553 data_time: 0.0102 memory: 13708 grad_norm: 5.4647 loss: 3.8251 top1_acc: 0.0625 top5_acc: 0.4375 loss_cls: 3.8251 2023/02/17 23:14:05 - mmengine - INFO - Epoch(train) [1][1160/1320] lr: 2.0000e-03 eta: 5:16:05 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 5.4068 loss: 3.6884 top1_acc: 0.0625 top5_acc: 0.5000 loss_cls: 3.6884 2023/02/17 23:14:10 - mmengine - INFO - Epoch(train) [1][1180/1320] lr: 2.0000e-03 eta: 5:15:19 time: 0.2563 data_time: 0.0106 memory: 13708 grad_norm: 5.4755 loss: 3.6850 top1_acc: 0.1250 top5_acc: 0.5625 loss_cls: 3.6850 2023/02/17 23:14:15 - mmengine - INFO - Epoch(train) [1][1200/1320] lr: 2.0000e-03 eta: 5:14:35 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 5.4725 loss: 3.7109 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 3.7109 2023/02/17 23:14:20 - mmengine - INFO - Epoch(train) [1][1220/1320] lr: 2.0000e-03 eta: 5:13:51 time: 0.2558 data_time: 0.0112 memory: 13708 grad_norm: 5.4874 loss: 3.6930 top1_acc: 0.0625 top5_acc: 0.2500 loss_cls: 3.6930 2023/02/17 23:14:25 - mmengine - INFO - Epoch(train) [1][1240/1320] lr: 2.0000e-03 eta: 5:13:09 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 5.4871 loss: 3.7647 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 3.7647 2023/02/17 23:14:30 - mmengine - INFO - Epoch(train) [1][1260/1320] lr: 2.0000e-03 eta: 5:12:28 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 5.5214 loss: 3.6781 top1_acc: 0.1875 top5_acc: 0.3750 loss_cls: 3.6781 2023/02/17 23:14:35 - mmengine - INFO - Epoch(train) [1][1280/1320] lr: 2.0000e-03 eta: 5:11:47 time: 0.2542 data_time: 0.0108 memory: 13708 grad_norm: 5.5818 loss: 3.6255 top1_acc: 0.1250 top5_acc: 0.3125 loss_cls: 3.6255 2023/02/17 23:14:40 - mmengine - INFO - Epoch(train) [1][1300/1320] lr: 2.0000e-03 eta: 5:11:06 time: 0.2546 data_time: 0.0106 memory: 13708 grad_norm: 5.5534 loss: 3.5864 top1_acc: 0.0625 top5_acc: 0.3125 loss_cls: 3.5864 2023/02/17 23:14:45 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:14:45 - mmengine - INFO - Epoch(train) [1][1320/1320] lr: 2.0000e-03 eta: 5:10:24 time: 0.2509 data_time: 0.0107 memory: 13708 grad_norm: 5.6429 loss: 3.6618 top1_acc: 0.0909 top5_acc: 0.3636 loss_cls: 3.6618 2023/02/17 23:15:31 - mmengine - INFO - Epoch(val) [1][ 20/194] eta: 0:06:36 time: 2.2788 data_time: 2.2088 memory: 1818 2023/02/17 23:15:33 - mmengine - INFO - Epoch(val) [1][ 40/194] eta: 0:03:02 time: 0.0876 data_time: 0.0202 memory: 1818 2023/02/17 23:15:34 - mmengine - INFO - Epoch(val) [1][ 60/194] eta: 0:01:49 time: 0.0831 data_time: 0.0164 memory: 1818 2023/02/17 23:15:36 - mmengine - INFO - Epoch(val) [1][ 80/194] eta: 0:01:12 time: 0.0828 data_time: 0.0155 memory: 1818 2023/02/17 23:15:38 - mmengine - INFO - Epoch(val) [1][100/194] eta: 0:00:49 time: 0.0829 data_time: 0.0151 memory: 1818 2023/02/17 23:15:39 - mmengine - INFO - Epoch(val) [1][120/194] eta: 0:00:33 time: 0.0868 data_time: 0.0197 memory: 1818 2023/02/17 23:15:41 - mmengine - INFO - Epoch(val) [1][140/194] eta: 0:00:21 time: 0.0885 data_time: 0.0218 memory: 1818 2023/02/17 23:15:43 - mmengine - INFO - Epoch(val) [1][160/194] eta: 0:00:12 time: 0.0866 data_time: 0.0189 memory: 1818 2023/02/17 23:15:45 - mmengine - INFO - Epoch(val) [1][180/194] eta: 0:00:04 time: 0.0845 data_time: 0.0169 memory: 1818 2023/02/17 23:15:47 - mmengine - INFO - Epoch(val) [1][194/194] acc/top1: 0.1832 acc/top5: 0.4396 acc/mean1: 0.1228 2023/02/17 23:15:48 - mmengine - INFO - The best checkpoint with 0.1832 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2023/02/17 23:15:54 - mmengine - INFO - Epoch(train) [2][ 20/1320] lr: 6.5000e-03 eta: 5:10:25 time: 0.2956 data_time: 0.0440 memory: 13708 grad_norm: 5.6959 loss: 3.7343 top1_acc: 0.1875 top5_acc: 0.3750 loss_cls: 3.7343 2023/02/17 23:15:59 - mmengine - INFO - Epoch(train) [2][ 40/1320] lr: 6.5000e-03 eta: 5:09:49 time: 0.2560 data_time: 0.0121 memory: 13708 grad_norm: 6.1213 loss: 3.9475 top1_acc: 0.0000 top5_acc: 0.3125 loss_cls: 3.9475 2023/02/17 23:16:05 - mmengine - INFO - Epoch(train) [2][ 60/1320] lr: 6.5000e-03 eta: 5:09:14 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 5.8380 loss: 3.8362 top1_acc: 0.1875 top5_acc: 0.2500 loss_cls: 3.8362 2023/02/17 23:16:10 - mmengine - INFO - Epoch(train) [2][ 80/1320] lr: 6.5000e-03 eta: 5:08:39 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 5.7827 loss: 3.8221 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.8221 2023/02/17 23:16:15 - mmengine - INFO - Epoch(train) [2][ 100/1320] lr: 6.5000e-03 eta: 5:08:05 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 5.8194 loss: 3.7128 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 3.7128 2023/02/17 23:16:20 - mmengine - INFO - Epoch(train) [2][ 120/1320] lr: 6.5000e-03 eta: 5:07:32 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 5.8115 loss: 3.8214 top1_acc: 0.0000 top5_acc: 0.1875 loss_cls: 3.8214 2023/02/17 23:16:25 - mmengine - INFO - Epoch(train) [2][ 140/1320] lr: 6.5000e-03 eta: 5:07:00 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 5.6870 loss: 3.7624 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 3.7624 2023/02/17 23:16:30 - mmengine - INFO - Epoch(train) [2][ 160/1320] lr: 6.5000e-03 eta: 5:06:29 time: 0.2562 data_time: 0.0110 memory: 13708 grad_norm: 5.7666 loss: 3.7306 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 3.7306 2023/02/17 23:16:35 - mmengine - INFO - Epoch(train) [2][ 180/1320] lr: 6.5000e-03 eta: 5:05:58 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 5.6840 loss: 3.7022 top1_acc: 0.1250 top5_acc: 0.5000 loss_cls: 3.7022 2023/02/17 23:16:40 - mmengine - INFO - Epoch(train) [2][ 200/1320] lr: 6.5000e-03 eta: 5:05:27 time: 0.2550 data_time: 0.0109 memory: 13708 grad_norm: 5.6898 loss: 3.6537 top1_acc: 0.1875 top5_acc: 0.3125 loss_cls: 3.6537 2023/02/17 23:16:45 - mmengine - INFO - Epoch(train) [2][ 220/1320] lr: 6.5000e-03 eta: 5:04:57 time: 0.2545 data_time: 0.0103 memory: 13708 grad_norm: 5.6410 loss: 3.5562 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 3.5562 2023/02/17 23:16:51 - mmengine - INFO - Epoch(train) [2][ 240/1320] lr: 6.5000e-03 eta: 5:04:27 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 5.6576 loss: 3.6474 top1_acc: 0.1875 top5_acc: 0.3125 loss_cls: 3.6474 2023/02/17 23:16:56 - mmengine - INFO - Epoch(train) [2][ 260/1320] lr: 6.5000e-03 eta: 5:03:58 time: 0.2544 data_time: 0.0106 memory: 13708 grad_norm: 5.6904 loss: 3.7272 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 3.7272 2023/02/17 23:17:01 - mmengine - INFO - Epoch(train) [2][ 280/1320] lr: 6.5000e-03 eta: 5:03:29 time: 0.2543 data_time: 0.0103 memory: 13708 grad_norm: 5.6408 loss: 3.5686 top1_acc: 0.1250 top5_acc: 0.6250 loss_cls: 3.5686 2023/02/17 23:17:06 - mmengine - INFO - Epoch(train) [2][ 300/1320] lr: 6.5000e-03 eta: 5:03:02 time: 0.2556 data_time: 0.0112 memory: 13708 grad_norm: 5.7370 loss: 3.4734 top1_acc: 0.2500 top5_acc: 0.3750 loss_cls: 3.4734 2023/02/17 23:17:11 - mmengine - INFO - Epoch(train) [2][ 320/1320] lr: 6.5000e-03 eta: 5:02:34 time: 0.2548 data_time: 0.0111 memory: 13708 grad_norm: 5.6537 loss: 3.4354 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 3.4354 2023/02/17 23:17:16 - mmengine - INFO - Epoch(train) [2][ 340/1320] lr: 6.5000e-03 eta: 5:02:08 time: 0.2557 data_time: 0.0114 memory: 13708 grad_norm: 5.7542 loss: 3.4256 top1_acc: 0.1875 top5_acc: 0.3750 loss_cls: 3.4256 2023/02/17 23:17:21 - mmengine - INFO - Epoch(train) [2][ 360/1320] lr: 6.5000e-03 eta: 5:01:43 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 5.6082 loss: 3.3900 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.3900 2023/02/17 23:17:26 - mmengine - INFO - Epoch(train) [2][ 380/1320] lr: 6.5000e-03 eta: 5:01:18 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 5.5916 loss: 3.4419 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 3.4419 2023/02/17 23:17:31 - mmengine - INFO - Epoch(train) [2][ 400/1320] lr: 6.5000e-03 eta: 5:00:53 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 5.7609 loss: 3.5262 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 3.5262 2023/02/17 23:17:36 - mmengine - INFO - Epoch(train) [2][ 420/1320] lr: 6.5000e-03 eta: 5:00:28 time: 0.2557 data_time: 0.0112 memory: 13708 grad_norm: 5.7727 loss: 3.5150 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 3.5150 2023/02/17 23:17:42 - mmengine - INFO - Epoch(train) [2][ 440/1320] lr: 6.5000e-03 eta: 5:00:04 time: 0.2547 data_time: 0.0109 memory: 13708 grad_norm: 5.6517 loss: 3.4366 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 3.4366 2023/02/17 23:17:47 - mmengine - INFO - Epoch(train) [2][ 460/1320] lr: 6.5000e-03 eta: 4:59:40 time: 0.2550 data_time: 0.0109 memory: 13708 grad_norm: 5.7391 loss: 3.5574 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 3.5574 2023/02/17 23:17:52 - mmengine - INFO - Epoch(train) [2][ 480/1320] lr: 6.5000e-03 eta: 4:59:17 time: 0.2549 data_time: 0.0112 memory: 13708 grad_norm: 5.7028 loss: 3.3588 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 3.3588 2023/02/17 23:17:57 - mmengine - INFO - Epoch(train) [2][ 500/1320] lr: 6.5000e-03 eta: 4:58:53 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 5.6068 loss: 3.5595 top1_acc: 0.1250 top5_acc: 0.3125 loss_cls: 3.5595 2023/02/17 23:18:02 - mmengine - INFO - Epoch(train) [2][ 520/1320] lr: 6.5000e-03 eta: 4:58:31 time: 0.2547 data_time: 0.0110 memory: 13708 grad_norm: 5.7076 loss: 3.3159 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 3.3159 2023/02/17 23:18:07 - mmengine - INFO - Epoch(train) [2][ 540/1320] lr: 6.5000e-03 eta: 4:58:08 time: 0.2547 data_time: 0.0110 memory: 13708 grad_norm: 5.8009 loss: 3.1482 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 3.1482 2023/02/17 23:18:12 - mmengine - INFO - Epoch(train) [2][ 560/1320] lr: 6.5000e-03 eta: 4:57:46 time: 0.2549 data_time: 0.0110 memory: 13708 grad_norm: 5.6716 loss: 3.4271 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 3.4271 2023/02/17 23:18:17 - mmengine - INFO - Epoch(train) [2][ 580/1320] lr: 6.5000e-03 eta: 4:57:25 time: 0.2552 data_time: 0.0112 memory: 13708 grad_norm: 5.8095 loss: 3.3682 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 3.3682 2023/02/17 23:18:22 - mmengine - INFO - Epoch(train) [2][ 600/1320] lr: 6.5000e-03 eta: 4:57:03 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 5.7920 loss: 3.0351 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.0351 2023/02/17 23:18:27 - mmengine - INFO - Epoch(train) [2][ 620/1320] lr: 6.5000e-03 eta: 4:56:43 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 5.7417 loss: 3.1450 top1_acc: 0.2500 top5_acc: 0.3750 loss_cls: 3.1450 2023/02/17 23:18:33 - mmengine - INFO - Epoch(train) [2][ 640/1320] lr: 6.5000e-03 eta: 4:56:22 time: 0.2543 data_time: 0.0108 memory: 13708 grad_norm: 5.7293 loss: 3.1913 top1_acc: 0.1250 top5_acc: 0.5000 loss_cls: 3.1913 2023/02/17 23:18:38 - mmengine - INFO - Epoch(train) [2][ 660/1320] lr: 6.5000e-03 eta: 4:56:02 time: 0.2558 data_time: 0.0120 memory: 13708 grad_norm: 5.6776 loss: 3.2153 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.2153 2023/02/17 23:18:43 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:18:43 - mmengine - INFO - Epoch(train) [2][ 680/1320] lr: 6.5000e-03 eta: 4:55:42 time: 0.2550 data_time: 0.0113 memory: 13708 grad_norm: 5.7567 loss: 3.2047 top1_acc: 0.0625 top5_acc: 0.3750 loss_cls: 3.2047 2023/02/17 23:18:48 - mmengine - INFO - Epoch(train) [2][ 700/1320] lr: 6.5000e-03 eta: 4:55:22 time: 0.2548 data_time: 0.0111 memory: 13708 grad_norm: 5.6777 loss: 3.1948 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.1948 2023/02/17 23:18:53 - mmengine - INFO - Epoch(train) [2][ 720/1320] lr: 6.5000e-03 eta: 4:55:03 time: 0.2544 data_time: 0.0107 memory: 13708 grad_norm: 5.7663 loss: 3.0757 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 3.0757 2023/02/17 23:18:58 - mmengine - INFO - Epoch(train) [2][ 740/1320] lr: 6.5000e-03 eta: 4:54:44 time: 0.2561 data_time: 0.0128 memory: 13708 grad_norm: 5.8608 loss: 3.1625 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 3.1625 2023/02/17 23:19:03 - mmengine - INFO - Epoch(train) [2][ 760/1320] lr: 6.5000e-03 eta: 4:54:25 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 5.8729 loss: 3.2749 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 3.2749 2023/02/17 23:19:08 - mmengine - INFO - Epoch(train) [2][ 780/1320] lr: 6.5000e-03 eta: 4:54:08 time: 0.2566 data_time: 0.0122 memory: 13708 grad_norm: 5.8691 loss: 3.0416 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 3.0416 2023/02/17 23:19:13 - mmengine - INFO - Epoch(train) [2][ 800/1320] lr: 6.5000e-03 eta: 4:53:49 time: 0.2549 data_time: 0.0110 memory: 13708 grad_norm: 5.8995 loss: 3.1810 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 3.1810 2023/02/17 23:19:18 - mmengine - INFO - Epoch(train) [2][ 820/1320] lr: 6.5000e-03 eta: 4:53:32 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 5.7347 loss: 3.2271 top1_acc: 0.5000 top5_acc: 0.5625 loss_cls: 3.2271 2023/02/17 23:19:24 - mmengine - INFO - Epoch(train) [2][ 840/1320] lr: 6.5000e-03 eta: 4:53:15 time: 0.2569 data_time: 0.0129 memory: 13708 grad_norm: 5.8074 loss: 3.0172 top1_acc: 0.0625 top5_acc: 0.5625 loss_cls: 3.0172 2023/02/17 23:19:29 - mmengine - INFO - Epoch(train) [2][ 860/1320] lr: 6.5000e-03 eta: 4:52:57 time: 0.2544 data_time: 0.0108 memory: 13708 grad_norm: 5.9097 loss: 2.9360 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.9360 2023/02/17 23:19:34 - mmengine - INFO - Epoch(train) [2][ 880/1320] lr: 6.5000e-03 eta: 4:52:39 time: 0.2545 data_time: 0.0110 memory: 13708 grad_norm: 5.8582 loss: 3.0837 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 3.0837 2023/02/17 23:19:39 - mmengine - INFO - Epoch(train) [2][ 900/1320] lr: 6.5000e-03 eta: 4:52:23 time: 0.2561 data_time: 0.0117 memory: 13708 grad_norm: 5.8068 loss: 3.1946 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 3.1946 2023/02/17 23:19:44 - mmengine - INFO - Epoch(train) [2][ 920/1320] lr: 6.5000e-03 eta: 4:52:07 time: 0.2567 data_time: 0.0121 memory: 13708 grad_norm: 5.8790 loss: 3.0125 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 3.0125 2023/02/17 23:19:49 - mmengine - INFO - Epoch(train) [2][ 940/1320] lr: 6.5000e-03 eta: 4:51:50 time: 0.2550 data_time: 0.0110 memory: 13708 grad_norm: 6.0017 loss: 3.0053 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 3.0053 2023/02/17 23:19:54 - mmengine - INFO - Epoch(train) [2][ 960/1320] lr: 6.5000e-03 eta: 4:51:34 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 5.8465 loss: 3.1232 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 3.1232 2023/02/17 23:19:59 - mmengine - INFO - Epoch(train) [2][ 980/1320] lr: 6.5000e-03 eta: 4:51:18 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 5.8139 loss: 3.2319 top1_acc: 0.3125 top5_acc: 0.3750 loss_cls: 3.2319 2023/02/17 23:20:04 - mmengine - INFO - Epoch(train) [2][1000/1320] lr: 6.5000e-03 eta: 4:51:02 time: 0.2551 data_time: 0.0114 memory: 13708 grad_norm: 5.8818 loss: 2.9448 top1_acc: 0.1250 top5_acc: 0.5000 loss_cls: 2.9448 2023/02/17 23:20:10 - mmengine - INFO - Epoch(train) [2][1020/1320] lr: 6.5000e-03 eta: 4:50:46 time: 0.2548 data_time: 0.0112 memory: 13708 grad_norm: 5.9185 loss: 2.9928 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 2.9928 2023/02/17 23:20:15 - mmengine - INFO - Epoch(train) [2][1040/1320] lr: 6.5000e-03 eta: 4:50:30 time: 0.2555 data_time: 0.0110 memory: 13708 grad_norm: 5.8103 loss: 2.9251 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.9251 2023/02/17 23:20:20 - mmengine - INFO - Epoch(train) [2][1060/1320] lr: 6.5000e-03 eta: 4:50:15 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 5.8902 loss: 2.9048 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.9048 2023/02/17 23:20:25 - mmengine - INFO - Epoch(train) [2][1080/1320] lr: 6.5000e-03 eta: 4:49:59 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 6.0326 loss: 2.8671 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.8671 2023/02/17 23:20:30 - mmengine - INFO - Epoch(train) [2][1100/1320] lr: 6.5000e-03 eta: 4:49:44 time: 0.2550 data_time: 0.0111 memory: 13708 grad_norm: 5.8621 loss: 3.0114 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 3.0114 2023/02/17 23:20:35 - mmengine - INFO - Epoch(train) [2][1120/1320] lr: 6.5000e-03 eta: 4:49:29 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 5.7175 loss: 3.0274 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 3.0274 2023/02/17 23:20:40 - mmengine - INFO - Epoch(train) [2][1140/1320] lr: 6.5000e-03 eta: 4:49:14 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 5.9717 loss: 2.7936 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.7936 2023/02/17 23:20:45 - mmengine - INFO - Epoch(train) [2][1160/1320] lr: 6.5000e-03 eta: 4:49:00 time: 0.2559 data_time: 0.0116 memory: 13708 grad_norm: 5.8422 loss: 2.9264 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.9264 2023/02/17 23:20:50 - mmengine - INFO - Epoch(train) [2][1180/1320] lr: 6.5000e-03 eta: 4:48:45 time: 0.2546 data_time: 0.0112 memory: 13708 grad_norm: 5.9105 loss: 2.7485 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.7485 2023/02/17 23:20:55 - mmengine - INFO - Epoch(train) [2][1200/1320] lr: 6.5000e-03 eta: 4:48:30 time: 0.2545 data_time: 0.0109 memory: 13708 grad_norm: 5.9579 loss: 2.6675 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.6675 2023/02/17 23:21:01 - mmengine - INFO - Epoch(train) [2][1220/1320] lr: 6.5000e-03 eta: 4:48:16 time: 0.2544 data_time: 0.0112 memory: 13708 grad_norm: 6.0090 loss: 3.2332 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 3.2332 2023/02/17 23:21:06 - mmengine - INFO - Epoch(train) [2][1240/1320] lr: 6.5000e-03 eta: 4:48:02 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 5.9586 loss: 2.8954 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.8954 2023/02/17 23:21:11 - mmengine - INFO - Epoch(train) [2][1260/1320] lr: 6.5000e-03 eta: 4:47:47 time: 0.2547 data_time: 0.0110 memory: 13708 grad_norm: 5.9551 loss: 2.9165 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.9165 2023/02/17 23:21:16 - mmengine - INFO - Epoch(train) [2][1280/1320] lr: 6.5000e-03 eta: 4:47:34 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 5.9575 loss: 2.6857 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.6857 2023/02/17 23:21:21 - mmengine - INFO - Epoch(train) [2][1300/1320] lr: 6.5000e-03 eta: 4:47:20 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 6.1138 loss: 2.8020 top1_acc: 0.1875 top5_acc: 0.3750 loss_cls: 2.8020 2023/02/17 23:21:26 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:21:26 - mmengine - INFO - Epoch(train) [2][1320/1320] lr: 6.5000e-03 eta: 4:47:04 time: 0.2505 data_time: 0.0111 memory: 13708 grad_norm: 6.0633 loss: 2.8934 top1_acc: 0.0909 top5_acc: 0.4545 loss_cls: 2.8934 2023/02/17 23:21:28 - mmengine - INFO - Epoch(val) [2][ 20/194] eta: 0:00:21 time: 0.1221 data_time: 0.0539 memory: 1818 2023/02/17 23:21:30 - mmengine - INFO - Epoch(val) [2][ 40/194] eta: 0:00:16 time: 0.0893 data_time: 0.0216 memory: 1818 2023/02/17 23:21:32 - mmengine - INFO - Epoch(val) [2][ 60/194] eta: 0:00:13 time: 0.0872 data_time: 0.0193 memory: 1818 2023/02/17 23:21:34 - mmengine - INFO - Epoch(val) [2][ 80/194] eta: 0:00:11 time: 0.1018 data_time: 0.0341 memory: 1818 2023/02/17 23:21:36 - mmengine - INFO - Epoch(val) [2][100/194] eta: 0:00:09 time: 0.0899 data_time: 0.0202 memory: 1818 2023/02/17 23:21:37 - mmengine - INFO - Epoch(val) [2][120/194] eta: 0:00:07 time: 0.0842 data_time: 0.0146 memory: 1818 2023/02/17 23:21:39 - mmengine - INFO - Epoch(val) [2][140/194] eta: 0:00:05 time: 0.0864 data_time: 0.0184 memory: 1818 2023/02/17 23:21:41 - mmengine - INFO - Epoch(val) [2][160/194] eta: 0:00:03 time: 0.0825 data_time: 0.0134 memory: 1818 2023/02/17 23:21:43 - mmengine - INFO - Epoch(val) [2][180/194] eta: 0:00:01 time: 0.0855 data_time: 0.0175 memory: 1818 2023/02/17 23:21:44 - mmengine - INFO - Epoch(val) [2][194/194] acc/top1: 0.3307 acc/top5: 0.6145 acc/mean1: 0.2538 2023/02/17 23:21:45 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_1.pth is removed 2023/02/17 23:21:45 - mmengine - INFO - The best checkpoint with 0.3307 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2023/02/17 23:21:51 - mmengine - INFO - Epoch(train) [3][ 20/1320] lr: 1.1000e-02 eta: 4:47:09 time: 0.2933 data_time: 0.0386 memory: 13708 grad_norm: 6.1017 loss: 3.0362 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 3.0362 2023/02/17 23:21:56 - mmengine - INFO - Epoch(train) [3][ 40/1320] lr: 1.1000e-02 eta: 4:46:55 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 6.1132 loss: 3.1707 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 3.1707 2023/02/17 23:22:01 - mmengine - INFO - Epoch(train) [3][ 60/1320] lr: 1.1000e-02 eta: 4:46:42 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 5.8910 loss: 3.0795 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 3.0795 2023/02/17 23:22:06 - mmengine - INFO - Epoch(train) [3][ 80/1320] lr: 1.1000e-02 eta: 4:46:29 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 5.7702 loss: 2.9426 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.9426 2023/02/17 23:22:12 - mmengine - INFO - Epoch(train) [3][ 100/1320] lr: 1.1000e-02 eta: 4:46:16 time: 0.2550 data_time: 0.0111 memory: 13708 grad_norm: 5.6881 loss: 2.9740 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.9740 2023/02/17 23:22:17 - mmengine - INFO - Epoch(train) [3][ 120/1320] lr: 1.1000e-02 eta: 4:46:02 time: 0.2539 data_time: 0.0105 memory: 13708 grad_norm: 5.8773 loss: 2.9622 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.9622 2023/02/17 23:22:22 - mmengine - INFO - Epoch(train) [3][ 140/1320] lr: 1.1000e-02 eta: 4:45:49 time: 0.2546 data_time: 0.0105 memory: 13708 grad_norm: 5.6911 loss: 3.0146 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 3.0146 2023/02/17 23:22:27 - mmengine - INFO - Epoch(train) [3][ 160/1320] lr: 1.1000e-02 eta: 4:45:37 time: 0.2553 data_time: 0.0112 memory: 13708 grad_norm: 5.6513 loss: 3.0648 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.0648 2023/02/17 23:22:32 - mmengine - INFO - Epoch(train) [3][ 180/1320] lr: 1.1000e-02 eta: 4:45:24 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 5.7816 loss: 2.9557 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 2.9557 2023/02/17 23:22:37 - mmengine - INFO - Epoch(train) [3][ 200/1320] lr: 1.1000e-02 eta: 4:45:12 time: 0.2552 data_time: 0.0112 memory: 13708 grad_norm: 5.6115 loss: 3.1286 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 3.1286 2023/02/17 23:22:42 - mmengine - INFO - Epoch(train) [3][ 220/1320] lr: 1.1000e-02 eta: 4:44:59 time: 0.2554 data_time: 0.0114 memory: 13708 grad_norm: 5.7034 loss: 3.0052 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 3.0052 2023/02/17 23:22:47 - mmengine - INFO - Epoch(train) [3][ 240/1320] lr: 1.1000e-02 eta: 4:44:47 time: 0.2548 data_time: 0.0112 memory: 13708 grad_norm: 5.6926 loss: 3.1789 top1_acc: 0.3750 top5_acc: 0.3750 loss_cls: 3.1789 2023/02/17 23:22:52 - mmengine - INFO - Epoch(train) [3][ 260/1320] lr: 1.1000e-02 eta: 4:44:35 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 5.6591 loss: 2.9281 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.9281 2023/02/17 23:22:57 - mmengine - INFO - Epoch(train) [3][ 280/1320] lr: 1.1000e-02 eta: 4:44:23 time: 0.2555 data_time: 0.0112 memory: 13708 grad_norm: 5.6133 loss: 2.8842 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.8842 2023/02/17 23:23:03 - mmengine - INFO - Epoch(train) [3][ 300/1320] lr: 1.1000e-02 eta: 4:44:11 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 5.6073 loss: 2.8523 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.8523 2023/02/17 23:23:08 - mmengine - INFO - Epoch(train) [3][ 320/1320] lr: 1.1000e-02 eta: 4:43:59 time: 0.2561 data_time: 0.0118 memory: 13708 grad_norm: 5.5513 loss: 2.9891 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.9891 2023/02/17 23:23:13 - mmengine - INFO - Epoch(train) [3][ 340/1320] lr: 1.1000e-02 eta: 4:43:47 time: 0.2547 data_time: 0.0114 memory: 13708 grad_norm: 5.4829 loss: 2.8440 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.8440 2023/02/17 23:23:18 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:23:18 - mmengine - INFO - Epoch(train) [3][ 360/1320] lr: 1.1000e-02 eta: 4:43:36 time: 0.2564 data_time: 0.0119 memory: 13708 grad_norm: 5.5070 loss: 2.8932 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.8932 2023/02/17 23:23:23 - mmengine - INFO - Epoch(train) [3][ 380/1320] lr: 1.1000e-02 eta: 4:43:25 time: 0.2558 data_time: 0.0116 memory: 13708 grad_norm: 5.5534 loss: 2.8163 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.8163 2023/02/17 23:23:28 - mmengine - INFO - Epoch(train) [3][ 400/1320] lr: 1.1000e-02 eta: 4:43:13 time: 0.2545 data_time: 0.0108 memory: 13708 grad_norm: 5.5546 loss: 3.1789 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 3.1789 2023/02/17 23:23:33 - mmengine - INFO - Epoch(train) [3][ 420/1320] lr: 1.1000e-02 eta: 4:43:01 time: 0.2556 data_time: 0.0111 memory: 13708 grad_norm: 5.6933 loss: 2.9942 top1_acc: 0.2500 top5_acc: 0.3750 loss_cls: 2.9942 2023/02/17 23:23:38 - mmengine - INFO - Epoch(train) [3][ 440/1320] lr: 1.1000e-02 eta: 4:42:50 time: 0.2556 data_time: 0.0112 memory: 13708 grad_norm: 5.5252 loss: 3.0452 top1_acc: 0.3750 top5_acc: 0.3750 loss_cls: 3.0452 2023/02/17 23:23:43 - mmengine - INFO - Epoch(train) [3][ 460/1320] lr: 1.1000e-02 eta: 4:42:39 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 5.5192 loss: 2.7653 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.7653 2023/02/17 23:23:49 - mmengine - INFO - Epoch(train) [3][ 480/1320] lr: 1.1000e-02 eta: 4:42:28 time: 0.2553 data_time: 0.0112 memory: 13708 grad_norm: 5.6373 loss: 2.9566 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.9566 2023/02/17 23:23:54 - mmengine - INFO - Epoch(train) [3][ 500/1320] lr: 1.1000e-02 eta: 4:42:17 time: 0.2545 data_time: 0.0108 memory: 13708 grad_norm: 5.4859 loss: 2.8816 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.8816 2023/02/17 23:23:59 - mmengine - INFO - Epoch(train) [3][ 520/1320] lr: 1.1000e-02 eta: 4:42:05 time: 0.2541 data_time: 0.0107 memory: 13708 grad_norm: 5.5549 loss: 2.7207 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.7207 2023/02/17 23:24:04 - mmengine - INFO - Epoch(train) [3][ 540/1320] lr: 1.1000e-02 eta: 4:41:54 time: 0.2542 data_time: 0.0109 memory: 13708 grad_norm: 5.4667 loss: 2.8051 top1_acc: 0.1250 top5_acc: 0.6250 loss_cls: 2.8051 2023/02/17 23:24:09 - mmengine - INFO - Epoch(train) [3][ 560/1320] lr: 1.1000e-02 eta: 4:41:43 time: 0.2556 data_time: 0.0116 memory: 13708 grad_norm: 5.3863 loss: 2.8481 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.8481 2023/02/17 23:24:14 - mmengine - INFO - Epoch(train) [3][ 580/1320] lr: 1.1000e-02 eta: 4:41:32 time: 0.2541 data_time: 0.0110 memory: 13708 grad_norm: 5.3828 loss: 2.8800 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.8800 2023/02/17 23:24:19 - mmengine - INFO - Epoch(train) [3][ 600/1320] lr: 1.1000e-02 eta: 4:41:21 time: 0.2548 data_time: 0.0111 memory: 13708 grad_norm: 5.4587 loss: 3.0064 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 3.0064 2023/02/17 23:24:24 - mmengine - INFO - Epoch(train) [3][ 620/1320] lr: 1.1000e-02 eta: 4:41:10 time: 0.2542 data_time: 0.0105 memory: 13708 grad_norm: 5.3731 loss: 2.8021 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.8021 2023/02/17 23:24:29 - mmengine - INFO - Epoch(train) [3][ 640/1320] lr: 1.1000e-02 eta: 4:40:59 time: 0.2546 data_time: 0.0113 memory: 13708 grad_norm: 5.4599 loss: 2.8730 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.8730 2023/02/17 23:24:34 - mmengine - INFO - Epoch(train) [3][ 660/1320] lr: 1.1000e-02 eta: 4:40:48 time: 0.2547 data_time: 0.0112 memory: 13708 grad_norm: 5.3530 loss: 2.9283 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.9283 2023/02/17 23:24:40 - mmengine - INFO - Epoch(train) [3][ 680/1320] lr: 1.1000e-02 eta: 4:40:39 time: 0.2584 data_time: 0.0149 memory: 13708 grad_norm: 5.3139 loss: 2.8769 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.8769 2023/02/17 23:24:45 - mmengine - INFO - Epoch(train) [3][ 700/1320] lr: 1.1000e-02 eta: 4:40:29 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 5.3945 loss: 2.7038 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.7038 2023/02/17 23:24:50 - mmengine - INFO - Epoch(train) [3][ 720/1320] lr: 1.1000e-02 eta: 4:40:18 time: 0.2550 data_time: 0.0111 memory: 13708 grad_norm: 5.3038 loss: 2.8291 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 2.8291 2023/02/17 23:24:55 - mmengine - INFO - Epoch(train) [3][ 740/1320] lr: 1.1000e-02 eta: 4:40:08 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 5.4583 loss: 2.7657 top1_acc: 0.1250 top5_acc: 0.5625 loss_cls: 2.7657 2023/02/17 23:25:00 - mmengine - INFO - Epoch(train) [3][ 760/1320] lr: 1.1000e-02 eta: 4:39:57 time: 0.2547 data_time: 0.0109 memory: 13708 grad_norm: 5.4944 loss: 2.9087 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.9087 2023/02/17 23:25:05 - mmengine - INFO - Epoch(train) [3][ 780/1320] lr: 1.1000e-02 eta: 4:39:47 time: 0.2553 data_time: 0.0105 memory: 13708 grad_norm: 5.2487 loss: 2.8100 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.8100 2023/02/17 23:25:10 - mmengine - INFO - Epoch(train) [3][ 800/1320] lr: 1.1000e-02 eta: 4:39:37 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 5.3204 loss: 2.7671 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.7671 2023/02/17 23:25:15 - mmengine - INFO - Epoch(train) [3][ 820/1320] lr: 1.1000e-02 eta: 4:39:27 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 5.2854 loss: 2.7559 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.7559 2023/02/17 23:25:20 - mmengine - INFO - Epoch(train) [3][ 840/1320] lr: 1.1000e-02 eta: 4:39:17 time: 0.2547 data_time: 0.0108 memory: 13708 grad_norm: 5.3188 loss: 2.8790 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.8790 2023/02/17 23:25:25 - mmengine - INFO - Epoch(train) [3][ 860/1320] lr: 1.1000e-02 eta: 4:39:07 time: 0.2555 data_time: 0.0113 memory: 13708 grad_norm: 5.4942 loss: 2.7866 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.7866 2023/02/17 23:25:31 - mmengine - INFO - Epoch(train) [3][ 880/1320] lr: 1.1000e-02 eta: 4:38:57 time: 0.2545 data_time: 0.0107 memory: 13708 grad_norm: 5.2963 loss: 2.8195 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.8195 2023/02/17 23:25:36 - mmengine - INFO - Epoch(train) [3][ 900/1320] lr: 1.1000e-02 eta: 4:38:47 time: 0.2547 data_time: 0.0111 memory: 13708 grad_norm: 5.5768 loss: 2.7420 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.7420 2023/02/17 23:25:41 - mmengine - INFO - Epoch(train) [3][ 920/1320] lr: 1.1000e-02 eta: 4:38:37 time: 0.2550 data_time: 0.0113 memory: 13708 grad_norm: 5.3859 loss: 2.9545 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.9545 2023/02/17 23:25:46 - mmengine - INFO - Epoch(train) [3][ 940/1320] lr: 1.1000e-02 eta: 4:38:27 time: 0.2556 data_time: 0.0123 memory: 13708 grad_norm: 5.3530 loss: 2.7440 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.7440 2023/02/17 23:25:51 - mmengine - INFO - Epoch(train) [3][ 960/1320] lr: 1.1000e-02 eta: 4:38:17 time: 0.2544 data_time: 0.0107 memory: 13708 grad_norm: 5.5588 loss: 2.7928 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.7928 2023/02/17 23:25:56 - mmengine - INFO - Epoch(train) [3][ 980/1320] lr: 1.1000e-02 eta: 4:38:08 time: 0.2550 data_time: 0.0109 memory: 13708 grad_norm: 5.5192 loss: 2.6173 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.6173 2023/02/17 23:26:01 - mmengine - INFO - Epoch(train) [3][1000/1320] lr: 1.1000e-02 eta: 4:37:58 time: 0.2546 data_time: 0.0110 memory: 13708 grad_norm: 5.2885 loss: 2.8266 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.8266 2023/02/17 23:26:06 - mmengine - INFO - Epoch(train) [3][1020/1320] lr: 1.1000e-02 eta: 4:37:49 time: 0.2561 data_time: 0.0123 memory: 13708 grad_norm: 5.4201 loss: 2.8499 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.8499 2023/02/17 23:26:11 - mmengine - INFO - Epoch(train) [3][1040/1320] lr: 1.1000e-02 eta: 4:37:39 time: 0.2553 data_time: 0.0105 memory: 13708 grad_norm: 5.4022 loss: 2.7920 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.7920 2023/02/17 23:26:16 - mmengine - INFO - Epoch(train) [3][1060/1320] lr: 1.1000e-02 eta: 4:37:30 time: 0.2545 data_time: 0.0109 memory: 13708 grad_norm: 5.2678 loss: 2.7600 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.7600 2023/02/17 23:26:22 - mmengine - INFO - Epoch(train) [3][1080/1320] lr: 1.1000e-02 eta: 4:37:20 time: 0.2547 data_time: 0.0109 memory: 13708 grad_norm: 5.1925 loss: 2.6874 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 2.6874 2023/02/17 23:26:27 - mmengine - INFO - Epoch(train) [3][1100/1320] lr: 1.1000e-02 eta: 4:37:10 time: 0.2542 data_time: 0.0106 memory: 13708 grad_norm: 5.3672 loss: 2.8613 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.8613 2023/02/17 23:26:32 - mmengine - INFO - Epoch(train) [3][1120/1320] lr: 1.1000e-02 eta: 4:37:01 time: 0.2544 data_time: 0.0110 memory: 13708 grad_norm: 5.4730 loss: 2.7515 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.7515 2023/02/17 23:26:37 - mmengine - INFO - Epoch(train) [3][1140/1320] lr: 1.1000e-02 eta: 4:36:52 time: 0.2555 data_time: 0.0110 memory: 13708 grad_norm: 5.2337 loss: 2.6016 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.6016 2023/02/17 23:26:42 - mmengine - INFO - Epoch(train) [3][1160/1320] lr: 1.1000e-02 eta: 4:36:42 time: 0.2543 data_time: 0.0104 memory: 13708 grad_norm: 5.3025 loss: 2.4935 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.4935 2023/02/17 23:26:47 - mmengine - INFO - Epoch(train) [3][1180/1320] lr: 1.1000e-02 eta: 4:36:33 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 5.2281 loss: 2.8638 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.8638 2023/02/17 23:26:52 - mmengine - INFO - Epoch(train) [3][1200/1320] lr: 1.1000e-02 eta: 4:36:24 time: 0.2551 data_time: 0.0111 memory: 13708 grad_norm: 5.3132 loss: 2.7213 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.7213 2023/02/17 23:26:57 - mmengine - INFO - Epoch(train) [3][1220/1320] lr: 1.1000e-02 eta: 4:36:14 time: 0.2545 data_time: 0.0108 memory: 13708 grad_norm: 5.4532 loss: 2.7102 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.7102 2023/02/17 23:27:02 - mmengine - INFO - Epoch(train) [3][1240/1320] lr: 1.1000e-02 eta: 4:36:05 time: 0.2542 data_time: 0.0109 memory: 13708 grad_norm: 5.3686 loss: 2.6207 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.6207 2023/02/17 23:27:07 - mmengine - INFO - Epoch(train) [3][1260/1320] lr: 1.1000e-02 eta: 4:35:56 time: 0.2543 data_time: 0.0107 memory: 13708 grad_norm: 5.3194 loss: 2.6138 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.6138 2023/02/17 23:27:12 - mmengine - INFO - Epoch(train) [3][1280/1320] lr: 1.1000e-02 eta: 4:35:47 time: 0.2548 data_time: 0.0113 memory: 13708 grad_norm: 5.4099 loss: 2.6243 top1_acc: 0.1250 top5_acc: 0.6875 loss_cls: 2.6243 2023/02/17 23:27:18 - mmengine - INFO - Epoch(train) [3][1300/1320] lr: 1.1000e-02 eta: 4:35:38 time: 0.2546 data_time: 0.0111 memory: 13708 grad_norm: 5.2823 loss: 2.7633 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.7633 2023/02/17 23:27:23 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:27:23 - mmengine - INFO - Epoch(train) [3][1320/1320] lr: 1.1000e-02 eta: 4:35:27 time: 0.2503 data_time: 0.0100 memory: 13708 grad_norm: 5.3948 loss: 2.7060 top1_acc: 0.3636 top5_acc: 0.5455 loss_cls: 2.7060 2023/02/17 23:27:23 - mmengine - INFO - Saving checkpoint at 3 epochs 2023/02/17 23:27:26 - mmengine - INFO - Epoch(val) [3][ 20/194] eta: 0:00:22 time: 0.1297 data_time: 0.0620 memory: 1818 2023/02/17 23:27:28 - mmengine - INFO - Epoch(val) [3][ 40/194] eta: 0:00:16 time: 0.0890 data_time: 0.0215 memory: 1818 2023/02/17 23:27:30 - mmengine - INFO - Epoch(val) [3][ 60/194] eta: 0:00:13 time: 0.0875 data_time: 0.0193 memory: 1818 2023/02/17 23:27:31 - mmengine - INFO - Epoch(val) [3][ 80/194] eta: 0:00:11 time: 0.0848 data_time: 0.0169 memory: 1818 2023/02/17 23:27:33 - mmengine - INFO - Epoch(val) [3][100/194] eta: 0:00:09 time: 0.0878 data_time: 0.0206 memory: 1818 2023/02/17 23:27:35 - mmengine - INFO - Epoch(val) [3][120/194] eta: 0:00:06 time: 0.0841 data_time: 0.0166 memory: 1818 2023/02/17 23:27:37 - mmengine - INFO - Epoch(val) [3][140/194] eta: 0:00:05 time: 0.0936 data_time: 0.0260 memory: 1818 2023/02/17 23:27:38 - mmengine - INFO - Epoch(val) [3][160/194] eta: 0:00:03 time: 0.0805 data_time: 0.0125 memory: 1818 2023/02/17 23:27:40 - mmengine - INFO - Epoch(val) [3][180/194] eta: 0:00:01 time: 0.0840 data_time: 0.0175 memory: 1818 2023/02/17 23:27:42 - mmengine - INFO - Epoch(val) [3][194/194] acc/top1: 0.3546 acc/top5: 0.6467 acc/mean1: 0.2748 2023/02/17 23:27:42 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_2.pth is removed 2023/02/17 23:27:43 - mmengine - INFO - The best checkpoint with 0.3546 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2023/02/17 23:27:48 - mmengine - INFO - Epoch(train) [4][ 20/1320] lr: 1.5500e-02 eta: 4:35:30 time: 0.2939 data_time: 0.0430 memory: 13708 grad_norm: 5.5343 loss: 2.8665 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.8665 2023/02/17 23:27:54 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:27:54 - mmengine - INFO - Epoch(train) [4][ 40/1320] lr: 1.5500e-02 eta: 4:35:21 time: 0.2543 data_time: 0.0109 memory: 13708 grad_norm: 5.4369 loss: 2.8456 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.8456 2023/02/17 23:27:59 - mmengine - INFO - Epoch(train) [4][ 60/1320] lr: 1.5500e-02 eta: 4:35:12 time: 0.2547 data_time: 0.0109 memory: 13708 grad_norm: 5.1235 loss: 2.7521 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.7521 2023/02/17 23:28:04 - mmengine - INFO - Epoch(train) [4][ 80/1320] lr: 1.5500e-02 eta: 4:35:04 time: 0.2548 data_time: 0.0109 memory: 13708 grad_norm: 5.2350 loss: 2.7242 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.7242 2023/02/17 23:28:09 - mmengine - INFO - Epoch(train) [4][ 100/1320] lr: 1.5500e-02 eta: 4:34:55 time: 0.2551 data_time: 0.0103 memory: 13708 grad_norm: 5.2044 loss: 2.9525 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.9525 2023/02/17 23:28:14 - mmengine - INFO - Epoch(train) [4][ 120/1320] lr: 1.5500e-02 eta: 4:34:46 time: 0.2548 data_time: 0.0111 memory: 13708 grad_norm: 5.1575 loss: 2.7511 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.7511 2023/02/17 23:28:19 - mmengine - INFO - Epoch(train) [4][ 140/1320] lr: 1.5500e-02 eta: 4:34:37 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 5.1280 loss: 2.8659 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.8659 2023/02/17 23:28:24 - mmengine - INFO - Epoch(train) [4][ 160/1320] lr: 1.5500e-02 eta: 4:34:28 time: 0.2553 data_time: 0.0111 memory: 13708 grad_norm: 5.1095 loss: 2.7479 top1_acc: 0.2500 top5_acc: 0.3125 loss_cls: 2.7479 2023/02/17 23:28:29 - mmengine - INFO - Epoch(train) [4][ 180/1320] lr: 1.5500e-02 eta: 4:34:20 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 5.0735 loss: 3.0140 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 3.0140 2023/02/17 23:28:34 - mmengine - INFO - Epoch(train) [4][ 200/1320] lr: 1.5500e-02 eta: 4:34:11 time: 0.2543 data_time: 0.0106 memory: 13708 grad_norm: 5.1200 loss: 2.7774 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.7774 2023/02/17 23:28:39 - mmengine - INFO - Epoch(train) [4][ 220/1320] lr: 1.5500e-02 eta: 4:34:03 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 5.1481 loss: 2.9273 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.9273 2023/02/17 23:28:45 - mmengine - INFO - Epoch(train) [4][ 240/1320] lr: 1.5500e-02 eta: 4:33:54 time: 0.2556 data_time: 0.0112 memory: 13708 grad_norm: 5.0734 loss: 2.8159 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.8159 2023/02/17 23:28:50 - mmengine - INFO - Epoch(train) [4][ 260/1320] lr: 1.5500e-02 eta: 4:33:46 time: 0.2544 data_time: 0.0107 memory: 13708 grad_norm: 5.0747 loss: 3.0003 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 3.0003 2023/02/17 23:28:55 - mmengine - INFO - Epoch(train) [4][ 280/1320] lr: 1.5500e-02 eta: 4:33:37 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.9862 loss: 2.5901 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.5901 2023/02/17 23:29:00 - mmengine - INFO - Epoch(train) [4][ 300/1320] lr: 1.5500e-02 eta: 4:33:29 time: 0.2553 data_time: 0.0111 memory: 13708 grad_norm: 5.1132 loss: 2.8541 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.8541 2023/02/17 23:29:05 - mmengine - INFO - Epoch(train) [4][ 320/1320] lr: 1.5500e-02 eta: 4:33:21 time: 0.2560 data_time: 0.0111 memory: 13708 grad_norm: 5.0234 loss: 2.7798 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.7798 2023/02/17 23:29:10 - mmengine - INFO - Epoch(train) [4][ 340/1320] lr: 1.5500e-02 eta: 4:33:13 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 4.9408 loss: 2.8022 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.8022 2023/02/17 23:29:15 - mmengine - INFO - Epoch(train) [4][ 360/1320] lr: 1.5500e-02 eta: 4:33:04 time: 0.2544 data_time: 0.0107 memory: 13708 grad_norm: 5.0075 loss: 2.8795 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.8795 2023/02/17 23:29:20 - mmengine - INFO - Epoch(train) [4][ 380/1320] lr: 1.5500e-02 eta: 4:32:56 time: 0.2550 data_time: 0.0113 memory: 13708 grad_norm: 5.0485 loss: 2.6302 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.6302 2023/02/17 23:29:25 - mmengine - INFO - Epoch(train) [4][ 400/1320] lr: 1.5500e-02 eta: 4:32:48 time: 0.2576 data_time: 0.0134 memory: 13708 grad_norm: 4.8905 loss: 2.7783 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.7783 2023/02/17 23:29:31 - mmengine - INFO - Epoch(train) [4][ 420/1320] lr: 1.5500e-02 eta: 4:32:40 time: 0.2551 data_time: 0.0112 memory: 13708 grad_norm: 4.8134 loss: 2.6187 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.6187 2023/02/17 23:29:36 - mmengine - INFO - Epoch(train) [4][ 440/1320] lr: 1.5500e-02 eta: 4:32:32 time: 0.2548 data_time: 0.0111 memory: 13708 grad_norm: 5.0325 loss: 2.5528 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.5528 2023/02/17 23:29:41 - mmengine - INFO - Epoch(train) [4][ 460/1320] lr: 1.5500e-02 eta: 4:32:23 time: 0.2544 data_time: 0.0107 memory: 13708 grad_norm: 5.0448 loss: 2.4769 top1_acc: 0.1250 top5_acc: 0.6250 loss_cls: 2.4769 2023/02/17 23:29:46 - mmengine - INFO - Epoch(train) [4][ 480/1320] lr: 1.5500e-02 eta: 4:32:15 time: 0.2550 data_time: 0.0112 memory: 13708 grad_norm: 4.9378 loss: 2.5859 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.5859 2023/02/17 23:29:51 - mmengine - INFO - Epoch(train) [4][ 500/1320] lr: 1.5500e-02 eta: 4:32:07 time: 0.2549 data_time: 0.0110 memory: 13708 grad_norm: 5.0150 loss: 2.6918 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.6918 2023/02/17 23:29:56 - mmengine - INFO - Epoch(train) [4][ 520/1320] lr: 1.5500e-02 eta: 4:31:59 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 4.9852 loss: 2.7961 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.7961 2023/02/17 23:30:01 - mmengine - INFO - Epoch(train) [4][ 540/1320] lr: 1.5500e-02 eta: 4:31:51 time: 0.2551 data_time: 0.0112 memory: 13708 grad_norm: 4.9940 loss: 2.6559 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 2.6559 2023/02/17 23:30:06 - mmengine - INFO - Epoch(train) [4][ 560/1320] lr: 1.5500e-02 eta: 4:31:42 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 5.1414 loss: 2.6593 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.6593 2023/02/17 23:30:11 - mmengine - INFO - Epoch(train) [4][ 580/1320] lr: 1.5500e-02 eta: 4:31:34 time: 0.2545 data_time: 0.0110 memory: 13708 grad_norm: 4.8124 loss: 2.5912 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.5912 2023/02/17 23:30:16 - mmengine - INFO - Epoch(train) [4][ 600/1320] lr: 1.5500e-02 eta: 4:31:26 time: 0.2554 data_time: 0.0112 memory: 13708 grad_norm: 4.9040 loss: 2.5728 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.5728 2023/02/17 23:30:22 - mmengine - INFO - Epoch(train) [4][ 620/1320] lr: 1.5500e-02 eta: 4:31:18 time: 0.2552 data_time: 0.0114 memory: 13708 grad_norm: 4.9552 loss: 2.7776 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.7776 2023/02/17 23:30:27 - mmengine - INFO - Epoch(train) [4][ 640/1320] lr: 1.5500e-02 eta: 4:31:10 time: 0.2550 data_time: 0.0111 memory: 13708 grad_norm: 4.9705 loss: 2.9481 top1_acc: 0.1875 top5_acc: 0.2500 loss_cls: 2.9481 2023/02/17 23:30:32 - mmengine - INFO - Epoch(train) [4][ 660/1320] lr: 1.5500e-02 eta: 4:31:03 time: 0.2560 data_time: 0.0114 memory: 13708 grad_norm: 4.8602 loss: 2.6258 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.6258 2023/02/17 23:30:37 - mmengine - INFO - Epoch(train) [4][ 680/1320] lr: 1.5500e-02 eta: 4:30:55 time: 0.2551 data_time: 0.0111 memory: 13708 grad_norm: 4.9836 loss: 2.7828 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.7828 2023/02/17 23:30:42 - mmengine - INFO - Epoch(train) [4][ 700/1320] lr: 1.5500e-02 eta: 4:30:47 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.8476 loss: 2.6305 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.6305 2023/02/17 23:30:47 - mmengine - INFO - Epoch(train) [4][ 720/1320] lr: 1.5500e-02 eta: 4:30:39 time: 0.2554 data_time: 0.0111 memory: 13708 grad_norm: 4.7309 loss: 2.7117 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.7117 2023/02/17 23:30:52 - mmengine - INFO - Epoch(train) [4][ 740/1320] lr: 1.5500e-02 eta: 4:30:31 time: 0.2545 data_time: 0.0103 memory: 13708 grad_norm: 4.9134 loss: 2.6591 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.6591 2023/02/17 23:30:57 - mmengine - INFO - Epoch(train) [4][ 760/1320] lr: 1.5500e-02 eta: 4:30:23 time: 0.2552 data_time: 0.0113 memory: 13708 grad_norm: 4.8854 loss: 2.7323 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.7323 2023/02/17 23:31:02 - mmengine - INFO - Epoch(train) [4][ 780/1320] lr: 1.5500e-02 eta: 4:30:16 time: 0.2552 data_time: 0.0110 memory: 13708 grad_norm: 4.7848 loss: 2.6840 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.6840 2023/02/17 23:31:07 - mmengine - INFO - Epoch(train) [4][ 800/1320] lr: 1.5500e-02 eta: 4:30:08 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.9330 loss: 2.6258 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.6258 2023/02/17 23:31:13 - mmengine - INFO - Epoch(train) [4][ 820/1320] lr: 1.5500e-02 eta: 4:30:00 time: 0.2561 data_time: 0.0120 memory: 13708 grad_norm: 4.8049 loss: 2.7055 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.7055 2023/02/17 23:31:18 - mmengine - INFO - Epoch(train) [4][ 840/1320] lr: 1.5500e-02 eta: 4:29:53 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.8921 loss: 2.6093 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.6093 2023/02/17 23:31:23 - mmengine - INFO - Epoch(train) [4][ 860/1320] lr: 1.5500e-02 eta: 4:29:45 time: 0.2551 data_time: 0.0111 memory: 13708 grad_norm: 4.8034 loss: 2.7671 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.7671 2023/02/17 23:31:28 - mmengine - INFO - Epoch(train) [4][ 880/1320] lr: 1.5500e-02 eta: 4:29:37 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 4.7169 loss: 2.7087 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.7087 2023/02/17 23:31:33 - mmengine - INFO - Epoch(train) [4][ 900/1320] lr: 1.5500e-02 eta: 4:29:30 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.7542 loss: 2.5518 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.5518 2023/02/17 23:31:38 - mmengine - INFO - Epoch(train) [4][ 920/1320] lr: 1.5500e-02 eta: 4:29:22 time: 0.2551 data_time: 0.0107 memory: 13708 grad_norm: 4.8637 loss: 2.5752 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.5752 2023/02/17 23:31:43 - mmengine - INFO - Epoch(train) [4][ 940/1320] lr: 1.5500e-02 eta: 4:29:15 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 4.8680 loss: 2.8336 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.8336 2023/02/17 23:31:48 - mmengine - INFO - Epoch(train) [4][ 960/1320] lr: 1.5500e-02 eta: 4:29:07 time: 0.2550 data_time: 0.0113 memory: 13708 grad_norm: 4.8123 loss: 2.7672 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.7672 2023/02/17 23:31:53 - mmengine - INFO - Epoch(train) [4][ 980/1320] lr: 1.5500e-02 eta: 4:29:00 time: 0.2555 data_time: 0.0110 memory: 13708 grad_norm: 4.9306 loss: 2.7407 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.7407 2023/02/17 23:31:59 - mmengine - INFO - Epoch(train) [4][1000/1320] lr: 1.5500e-02 eta: 4:28:52 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 4.7449 loss: 2.8939 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.8939 2023/02/17 23:32:04 - mmengine - INFO - Epoch(train) [4][1020/1320] lr: 1.5500e-02 eta: 4:28:45 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.7497 loss: 2.5217 top1_acc: 0.7500 top5_acc: 0.7500 loss_cls: 2.5217 2023/02/17 23:32:09 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:32:09 - mmengine - INFO - Epoch(train) [4][1040/1320] lr: 1.5500e-02 eta: 4:28:37 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.7759 loss: 2.7374 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.7374 2023/02/17 23:32:14 - mmengine - INFO - Epoch(train) [4][1060/1320] lr: 1.5500e-02 eta: 4:28:30 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 4.7852 loss: 2.7105 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.7105 2023/02/17 23:32:19 - mmengine - INFO - Epoch(train) [4][1080/1320] lr: 1.5500e-02 eta: 4:28:23 time: 0.2561 data_time: 0.0117 memory: 13708 grad_norm: 4.7867 loss: 2.7857 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.7857 2023/02/17 23:32:24 - mmengine - INFO - Epoch(train) [4][1100/1320] lr: 1.5500e-02 eta: 4:28:15 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.7866 loss: 2.5384 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.5384 2023/02/17 23:32:29 - mmengine - INFO - Epoch(train) [4][1120/1320] lr: 1.5500e-02 eta: 4:28:08 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 4.6936 loss: 2.7763 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 2.7763 2023/02/17 23:32:34 - mmengine - INFO - Epoch(train) [4][1140/1320] lr: 1.5500e-02 eta: 4:28:01 time: 0.2550 data_time: 0.0111 memory: 13708 grad_norm: 4.8420 loss: 2.6664 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.6664 2023/02/17 23:32:39 - mmengine - INFO - Epoch(train) [4][1160/1320] lr: 1.5500e-02 eta: 4:27:53 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.7156 loss: 2.8056 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.8056 2023/02/17 23:32:45 - mmengine - INFO - Epoch(train) [4][1180/1320] lr: 1.5500e-02 eta: 4:27:46 time: 0.2555 data_time: 0.0111 memory: 13708 grad_norm: 4.8147 loss: 2.6768 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.6768 2023/02/17 23:32:50 - mmengine - INFO - Epoch(train) [4][1200/1320] lr: 1.5500e-02 eta: 4:27:39 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.6971 loss: 2.7116 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.7116 2023/02/17 23:32:55 - mmengine - INFO - Epoch(train) [4][1220/1320] lr: 1.5500e-02 eta: 4:27:31 time: 0.2552 data_time: 0.0112 memory: 13708 grad_norm: 4.8163 loss: 2.5762 top1_acc: 0.3125 top5_acc: 0.3750 loss_cls: 2.5762 2023/02/17 23:33:00 - mmengine - INFO - Epoch(train) [4][1240/1320] lr: 1.5500e-02 eta: 4:27:24 time: 0.2556 data_time: 0.0112 memory: 13708 grad_norm: 4.8922 loss: 2.6143 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.6143 2023/02/17 23:33:05 - mmengine - INFO - Epoch(train) [4][1260/1320] lr: 1.5500e-02 eta: 4:27:17 time: 0.2572 data_time: 0.0132 memory: 13708 grad_norm: 4.8882 loss: 2.4278 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 2.4278 2023/02/17 23:33:10 - mmengine - INFO - Epoch(train) [4][1280/1320] lr: 1.5500e-02 eta: 4:27:10 time: 0.2563 data_time: 0.0113 memory: 13708 grad_norm: 4.7029 loss: 2.4074 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.4074 2023/02/17 23:33:15 - mmengine - INFO - Epoch(train) [4][1300/1320] lr: 1.5500e-02 eta: 4:27:03 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 4.8914 loss: 2.6442 top1_acc: 0.2500 top5_acc: 0.8125 loss_cls: 2.6442 2023/02/17 23:33:20 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:33:20 - mmengine - INFO - Epoch(train) [4][1320/1320] lr: 1.5500e-02 eta: 4:26:55 time: 0.2508 data_time: 0.0106 memory: 13708 grad_norm: 4.6252 loss: 2.6689 top1_acc: 0.2727 top5_acc: 0.7273 loss_cls: 2.6689 2023/02/17 23:33:23 - mmengine - INFO - Epoch(val) [4][ 20/194] eta: 0:00:23 time: 0.1347 data_time: 0.0673 memory: 1818 2023/02/17 23:33:25 - mmengine - INFO - Epoch(val) [4][ 40/194] eta: 0:00:17 time: 0.0872 data_time: 0.0201 memory: 1818 2023/02/17 23:33:27 - mmengine - INFO - Epoch(val) [4][ 60/194] eta: 0:00:13 time: 0.0904 data_time: 0.0214 memory: 1818 2023/02/17 23:33:28 - mmengine - INFO - Epoch(val) [4][ 80/194] eta: 0:00:11 time: 0.0846 data_time: 0.0171 memory: 1818 2023/02/17 23:33:30 - mmengine - INFO - Epoch(val) [4][100/194] eta: 0:00:09 time: 0.0878 data_time: 0.0207 memory: 1818 2023/02/17 23:33:32 - mmengine - INFO - Epoch(val) [4][120/194] eta: 0:00:07 time: 0.0870 data_time: 0.0198 memory: 1818 2023/02/17 23:33:34 - mmengine - INFO - Epoch(val) [4][140/194] eta: 0:00:05 time: 0.0898 data_time: 0.0222 memory: 1818 2023/02/17 23:33:35 - mmengine - INFO - Epoch(val) [4][160/194] eta: 0:00:03 time: 0.0801 data_time: 0.0121 memory: 1818 2023/02/17 23:33:37 - mmengine - INFO - Epoch(val) [4][180/194] eta: 0:00:01 time: 0.0849 data_time: 0.0171 memory: 1818 2023/02/17 23:33:39 - mmengine - INFO - Epoch(val) [4][194/194] acc/top1: 0.3719 acc/top5: 0.6691 acc/mean1: 0.3012 2023/02/17 23:33:39 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_3.pth is removed 2023/02/17 23:33:39 - mmengine - INFO - The best checkpoint with 0.3719 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2023/02/17 23:33:45 - mmengine - INFO - Epoch(train) [5][ 20/1320] lr: 2.0000e-02 eta: 4:26:56 time: 0.2951 data_time: 0.0464 memory: 13708 grad_norm: 4.7819 loss: 2.6048 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.6048 2023/02/17 23:33:50 - mmengine - INFO - Epoch(train) [5][ 40/1320] lr: 2.0000e-02 eta: 4:26:49 time: 0.2547 data_time: 0.0108 memory: 13708 grad_norm: 4.8160 loss: 2.5771 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.5771 2023/02/17 23:33:55 - mmengine - INFO - Epoch(train) [5][ 60/1320] lr: 2.0000e-02 eta: 4:26:42 time: 0.2539 data_time: 0.0104 memory: 13708 grad_norm: 4.7541 loss: 2.5764 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.5764 2023/02/17 23:34:01 - mmengine - INFO - Epoch(train) [5][ 80/1320] lr: 2.0000e-02 eta: 4:26:34 time: 0.2545 data_time: 0.0107 memory: 13708 grad_norm: 4.7338 loss: 2.6227 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.6227 2023/02/17 23:34:06 - mmengine - INFO - Epoch(train) [5][ 100/1320] lr: 2.0000e-02 eta: 4:26:27 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.7367 loss: 2.7657 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.7657 2023/02/17 23:34:11 - mmengine - INFO - Epoch(train) [5][ 120/1320] lr: 2.0000e-02 eta: 4:26:20 time: 0.2545 data_time: 0.0108 memory: 13708 grad_norm: 4.6613 loss: 2.5781 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.5781 2023/02/17 23:34:16 - mmengine - INFO - Epoch(train) [5][ 140/1320] lr: 2.0000e-02 eta: 4:26:12 time: 0.2549 data_time: 0.0115 memory: 13708 grad_norm: 4.7662 loss: 2.6158 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.6158 2023/02/17 23:34:21 - mmengine - INFO - Epoch(train) [5][ 160/1320] lr: 2.0000e-02 eta: 4:26:05 time: 0.2542 data_time: 0.0110 memory: 13708 grad_norm: 4.7972 loss: 2.5514 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.5514 2023/02/17 23:34:26 - mmengine - INFO - Epoch(train) [5][ 180/1320] lr: 2.0000e-02 eta: 4:25:58 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 4.7308 loss: 2.8934 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.8934 2023/02/17 23:34:31 - mmengine - INFO - Epoch(train) [5][ 200/1320] lr: 2.0000e-02 eta: 4:25:50 time: 0.2545 data_time: 0.0108 memory: 13708 grad_norm: 4.5931 loss: 2.4253 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.4253 2023/02/17 23:34:36 - mmengine - INFO - Epoch(train) [5][ 220/1320] lr: 2.0000e-02 eta: 4:25:43 time: 0.2551 data_time: 0.0103 memory: 13708 grad_norm: 4.7736 loss: 2.9086 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.9086 2023/02/17 23:34:41 - mmengine - INFO - Epoch(train) [5][ 240/1320] lr: 2.0000e-02 eta: 4:25:36 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 4.4504 loss: 2.6940 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.6940 2023/02/17 23:34:46 - mmengine - INFO - Epoch(train) [5][ 260/1320] lr: 2.0000e-02 eta: 4:25:29 time: 0.2549 data_time: 0.0110 memory: 13708 grad_norm: 4.6677 loss: 2.6490 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.6490 2023/02/17 23:34:52 - mmengine - INFO - Epoch(train) [5][ 280/1320] lr: 2.0000e-02 eta: 4:25:22 time: 0.2540 data_time: 0.0104 memory: 13708 grad_norm: 4.5799 loss: 2.6541 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.6541 2023/02/17 23:34:57 - mmengine - INFO - Epoch(train) [5][ 300/1320] lr: 2.0000e-02 eta: 4:25:15 time: 0.2545 data_time: 0.0111 memory: 13708 grad_norm: 4.6085 loss: 2.6988 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.6988 2023/02/17 23:35:02 - mmengine - INFO - Epoch(train) [5][ 320/1320] lr: 2.0000e-02 eta: 4:25:07 time: 0.2542 data_time: 0.0111 memory: 13708 grad_norm: 4.5127 loss: 2.6196 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.6196 2023/02/17 23:35:07 - mmengine - INFO - Epoch(train) [5][ 340/1320] lr: 2.0000e-02 eta: 4:25:00 time: 0.2546 data_time: 0.0110 memory: 13708 grad_norm: 4.6968 loss: 2.4956 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.4956 2023/02/17 23:35:12 - mmengine - INFO - Epoch(train) [5][ 360/1320] lr: 2.0000e-02 eta: 4:24:53 time: 0.2555 data_time: 0.0111 memory: 13708 grad_norm: 4.7021 loss: 2.7771 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.7771 2023/02/17 23:35:17 - mmengine - INFO - Epoch(train) [5][ 380/1320] lr: 2.0000e-02 eta: 4:24:46 time: 0.2547 data_time: 0.0108 memory: 13708 grad_norm: 4.4692 loss: 2.5696 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.5696 2023/02/17 23:35:22 - mmengine - INFO - Epoch(train) [5][ 400/1320] lr: 2.0000e-02 eta: 4:24:39 time: 0.2555 data_time: 0.0111 memory: 13708 grad_norm: 4.6271 loss: 2.6968 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.6968 2023/02/17 23:35:27 - mmengine - INFO - Epoch(train) [5][ 420/1320] lr: 2.0000e-02 eta: 4:24:32 time: 0.2545 data_time: 0.0113 memory: 13708 grad_norm: 4.6659 loss: 2.7496 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.7496 2023/02/17 23:35:32 - mmengine - INFO - Epoch(train) [5][ 440/1320] lr: 2.0000e-02 eta: 4:24:25 time: 0.2544 data_time: 0.0107 memory: 13708 grad_norm: 4.4352 loss: 2.6058 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.6058 2023/02/17 23:35:37 - mmengine - INFO - Epoch(train) [5][ 460/1320] lr: 2.0000e-02 eta: 4:24:18 time: 0.2550 data_time: 0.0115 memory: 13708 grad_norm: 4.5486 loss: 2.8051 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.8051 2023/02/17 23:35:42 - mmengine - INFO - Epoch(train) [5][ 480/1320] lr: 2.0000e-02 eta: 4:24:11 time: 0.2544 data_time: 0.0108 memory: 13708 grad_norm: 4.5700 loss: 2.6796 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.6796 2023/02/17 23:35:48 - mmengine - INFO - Epoch(train) [5][ 500/1320] lr: 2.0000e-02 eta: 4:24:04 time: 0.2546 data_time: 0.0111 memory: 13708 grad_norm: 4.4194 loss: 2.6241 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.6241 2023/02/17 23:35:53 - mmengine - INFO - Epoch(train) [5][ 520/1320] lr: 2.0000e-02 eta: 4:23:57 time: 0.2555 data_time: 0.0114 memory: 13708 grad_norm: 4.6059 loss: 2.6258 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 2.6258 2023/02/17 23:35:58 - mmengine - INFO - Epoch(train) [5][ 540/1320] lr: 2.0000e-02 eta: 4:23:50 time: 0.2544 data_time: 0.0108 memory: 13708 grad_norm: 4.5387 loss: 2.7061 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.7061 2023/02/17 23:36:03 - mmengine - INFO - Epoch(train) [5][ 560/1320] lr: 2.0000e-02 eta: 4:23:43 time: 0.2557 data_time: 0.0117 memory: 13708 grad_norm: 4.4691 loss: 2.5810 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.5810 2023/02/17 23:36:08 - mmengine - INFO - Epoch(train) [5][ 580/1320] lr: 2.0000e-02 eta: 4:23:36 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 4.6089 loss: 2.7796 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.7796 2023/02/17 23:36:13 - mmengine - INFO - Epoch(train) [5][ 600/1320] lr: 2.0000e-02 eta: 4:23:30 time: 0.2554 data_time: 0.0114 memory: 13708 grad_norm: 4.5527 loss: 2.5898 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.5898 2023/02/17 23:36:18 - mmengine - INFO - Epoch(train) [5][ 620/1320] lr: 2.0000e-02 eta: 4:23:23 time: 0.2559 data_time: 0.0116 memory: 13708 grad_norm: 4.5253 loss: 2.7050 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.7050 2023/02/17 23:36:23 - mmengine - INFO - Epoch(train) [5][ 640/1320] lr: 2.0000e-02 eta: 4:23:16 time: 0.2547 data_time: 0.0110 memory: 13708 grad_norm: 4.4070 loss: 2.7165 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.7165 2023/02/17 23:36:28 - mmengine - INFO - Epoch(train) [5][ 660/1320] lr: 2.0000e-02 eta: 4:23:09 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.4611 loss: 2.4173 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.4173 2023/02/17 23:36:34 - mmengine - INFO - Epoch(train) [5][ 680/1320] lr: 2.0000e-02 eta: 4:23:02 time: 0.2549 data_time: 0.0113 memory: 13708 grad_norm: 4.4463 loss: 2.5496 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.5496 2023/02/17 23:36:39 - mmengine - INFO - Epoch(train) [5][ 700/1320] lr: 2.0000e-02 eta: 4:22:55 time: 0.2548 data_time: 0.0110 memory: 13708 grad_norm: 4.4336 loss: 2.4072 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.4072 2023/02/17 23:36:44 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:36:44 - mmengine - INFO - Epoch(train) [5][ 720/1320] lr: 2.0000e-02 eta: 4:22:48 time: 0.2545 data_time: 0.0110 memory: 13708 grad_norm: 4.4484 loss: 2.6137 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.6137 2023/02/17 23:36:49 - mmengine - INFO - Epoch(train) [5][ 740/1320] lr: 2.0000e-02 eta: 4:22:42 time: 0.2546 data_time: 0.0109 memory: 13708 grad_norm: 4.4687 loss: 2.6083 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.6083 2023/02/17 23:36:54 - mmengine - INFO - Epoch(train) [5][ 760/1320] lr: 2.0000e-02 eta: 4:22:35 time: 0.2563 data_time: 0.0118 memory: 13708 grad_norm: 4.5112 loss: 2.5166 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 2.5166 2023/02/17 23:36:59 - mmengine - INFO - Epoch(train) [5][ 780/1320] lr: 2.0000e-02 eta: 4:22:28 time: 0.2555 data_time: 0.0120 memory: 13708 grad_norm: 4.5095 loss: 2.6568 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.6568 2023/02/17 23:37:04 - mmengine - INFO - Epoch(train) [5][ 800/1320] lr: 2.0000e-02 eta: 4:22:21 time: 0.2540 data_time: 0.0107 memory: 13708 grad_norm: 4.5706 loss: 2.5767 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.5767 2023/02/17 23:37:09 - mmengine - INFO - Epoch(train) [5][ 820/1320] lr: 2.0000e-02 eta: 4:22:15 time: 0.2552 data_time: 0.0114 memory: 13708 grad_norm: 4.3564 loss: 2.6998 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.6998 2023/02/17 23:37:14 - mmengine - INFO - Epoch(train) [5][ 840/1320] lr: 2.0000e-02 eta: 4:22:08 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.3273 loss: 2.4802 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.4802 2023/02/17 23:37:19 - mmengine - INFO - Epoch(train) [5][ 860/1320] lr: 2.0000e-02 eta: 4:22:01 time: 0.2541 data_time: 0.0107 memory: 13708 grad_norm: 4.4840 loss: 2.6147 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.6147 2023/02/17 23:37:25 - mmengine - INFO - Epoch(train) [5][ 880/1320] lr: 2.0000e-02 eta: 4:21:54 time: 0.2552 data_time: 0.0113 memory: 13708 grad_norm: 4.5869 loss: 2.5611 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 2.5611 2023/02/17 23:37:30 - mmengine - INFO - Epoch(train) [5][ 900/1320] lr: 2.0000e-02 eta: 4:21:47 time: 0.2546 data_time: 0.0107 memory: 13708 grad_norm: 4.4096 loss: 2.5956 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.5956 2023/02/17 23:37:35 - mmengine - INFO - Epoch(train) [5][ 920/1320] lr: 2.0000e-02 eta: 4:21:41 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 4.3941 loss: 2.8016 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.8016 2023/02/17 23:37:40 - mmengine - INFO - Epoch(train) [5][ 940/1320] lr: 2.0000e-02 eta: 4:21:34 time: 0.2549 data_time: 0.0112 memory: 13708 grad_norm: 4.5031 loss: 2.5571 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.5571 2023/02/17 23:37:45 - mmengine - INFO - Epoch(train) [5][ 960/1320] lr: 2.0000e-02 eta: 4:21:27 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.6220 loss: 2.5902 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.5902 2023/02/17 23:37:50 - mmengine - INFO - Epoch(train) [5][ 980/1320] lr: 2.0000e-02 eta: 4:21:20 time: 0.2546 data_time: 0.0110 memory: 13708 grad_norm: 4.3691 loss: 2.5647 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.5647 2023/02/17 23:37:55 - mmengine - INFO - Epoch(train) [5][1000/1320] lr: 2.0000e-02 eta: 4:21:14 time: 0.2546 data_time: 0.0110 memory: 13708 grad_norm: 4.2825 loss: 2.5175 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.5175 2023/02/17 23:38:00 - mmengine - INFO - Epoch(train) [5][1020/1320] lr: 2.0000e-02 eta: 4:21:07 time: 0.2548 data_time: 0.0110 memory: 13708 grad_norm: 4.4152 loss: 2.3966 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.3966 2023/02/17 23:38:05 - mmengine - INFO - Epoch(train) [5][1040/1320] lr: 2.0000e-02 eta: 4:21:00 time: 0.2556 data_time: 0.0111 memory: 13708 grad_norm: 4.3771 loss: 2.5636 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.5636 2023/02/17 23:38:10 - mmengine - INFO - Epoch(train) [5][1060/1320] lr: 2.0000e-02 eta: 4:20:54 time: 0.2568 data_time: 0.0123 memory: 13708 grad_norm: 4.2670 loss: 2.6250 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.6250 2023/02/17 23:38:16 - mmengine - INFO - Epoch(train) [5][1080/1320] lr: 2.0000e-02 eta: 4:20:47 time: 0.2552 data_time: 0.0110 memory: 13708 grad_norm: 4.4440 loss: 2.5323 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.5323 2023/02/17 23:38:21 - mmengine - INFO - Epoch(train) [5][1100/1320] lr: 2.0000e-02 eta: 4:20:41 time: 0.2558 data_time: 0.0112 memory: 13708 grad_norm: 4.3100 loss: 2.3562 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.3562 2023/02/17 23:38:26 - mmengine - INFO - Epoch(train) [5][1120/1320] lr: 2.0000e-02 eta: 4:20:34 time: 0.2545 data_time: 0.0107 memory: 13708 grad_norm: 4.3487 loss: 2.5322 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.5322 2023/02/17 23:38:31 - mmengine - INFO - Epoch(train) [5][1140/1320] lr: 2.0000e-02 eta: 4:20:28 time: 0.2567 data_time: 0.0121 memory: 13708 grad_norm: 4.2597 loss: 2.3974 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.3974 2023/02/17 23:38:36 - mmengine - INFO - Epoch(train) [5][1160/1320] lr: 2.0000e-02 eta: 4:20:22 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 4.2997 loss: 2.4942 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.4942 2023/02/17 23:38:41 - mmengine - INFO - Epoch(train) [5][1180/1320] lr: 2.0000e-02 eta: 4:20:15 time: 0.2546 data_time: 0.0108 memory: 13708 grad_norm: 4.2506 loss: 2.3615 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.3615 2023/02/17 23:38:46 - mmengine - INFO - Epoch(train) [5][1200/1320] lr: 2.0000e-02 eta: 4:20:08 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 4.2771 loss: 2.4602 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.4602 2023/02/17 23:38:51 - mmengine - INFO - Epoch(train) [5][1220/1320] lr: 2.0000e-02 eta: 4:20:02 time: 0.2544 data_time: 0.0110 memory: 13708 grad_norm: 4.2556 loss: 2.3506 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.3506 2023/02/17 23:38:56 - mmengine - INFO - Epoch(train) [5][1240/1320] lr: 2.0000e-02 eta: 4:19:55 time: 0.2551 data_time: 0.0112 memory: 13708 grad_norm: 4.4331 loss: 2.5321 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.5321 2023/02/17 23:39:01 - mmengine - INFO - Epoch(train) [5][1260/1320] lr: 2.0000e-02 eta: 4:19:49 time: 0.2553 data_time: 0.0113 memory: 13708 grad_norm: 4.3984 loss: 2.4089 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.4089 2023/02/17 23:39:07 - mmengine - INFO - Epoch(train) [5][1280/1320] lr: 2.0000e-02 eta: 4:19:42 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.2867 loss: 2.3265 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.3265 2023/02/17 23:39:12 - mmengine - INFO - Epoch(train) [5][1300/1320] lr: 2.0000e-02 eta: 4:19:36 time: 0.2562 data_time: 0.0113 memory: 13708 grad_norm: 4.3825 loss: 2.4040 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.4040 2023/02/17 23:39:17 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:39:17 - mmengine - INFO - Epoch(train) [5][1320/1320] lr: 2.0000e-02 eta: 4:19:28 time: 0.2508 data_time: 0.0105 memory: 13708 grad_norm: 4.4864 loss: 2.7552 top1_acc: 0.5455 top5_acc: 0.6364 loss_cls: 2.7552 2023/02/17 23:39:19 - mmengine - INFO - Epoch(val) [5][ 20/194] eta: 0:00:21 time: 0.1254 data_time: 0.0574 memory: 1818 2023/02/17 23:39:21 - mmengine - INFO - Epoch(val) [5][ 40/194] eta: 0:00:16 time: 0.0876 data_time: 0.0195 memory: 1818 2023/02/17 23:39:23 - mmengine - INFO - Epoch(val) [5][ 60/194] eta: 0:00:13 time: 0.0883 data_time: 0.0204 memory: 1818 2023/02/17 23:39:25 - mmengine - INFO - Epoch(val) [5][ 80/194] eta: 0:00:11 time: 0.0900 data_time: 0.0216 memory: 1818 2023/02/17 23:39:26 - mmengine - INFO - Epoch(val) [5][100/194] eta: 0:00:09 time: 0.0877 data_time: 0.0193 memory: 1818 2023/02/17 23:39:28 - mmengine - INFO - Epoch(val) [5][120/194] eta: 0:00:06 time: 0.0877 data_time: 0.0190 memory: 1818 2023/02/17 23:39:30 - mmengine - INFO - Epoch(val) [5][140/194] eta: 0:00:05 time: 0.0866 data_time: 0.0182 memory: 1818 2023/02/17 23:39:31 - mmengine - INFO - Epoch(val) [5][160/194] eta: 0:00:03 time: 0.0811 data_time: 0.0131 memory: 1818 2023/02/17 23:39:33 - mmengine - INFO - Epoch(val) [5][180/194] eta: 0:00:01 time: 0.0882 data_time: 0.0202 memory: 1818 2023/02/17 23:39:35 - mmengine - INFO - Epoch(val) [5][194/194] acc/top1: 0.3653 acc/top5: 0.6646 acc/mean1: 0.2892 2023/02/17 23:39:41 - mmengine - INFO - Epoch(train) [6][ 20/1320] lr: 2.0000e-02 eta: 4:19:30 time: 0.2987 data_time: 0.0458 memory: 13708 grad_norm: 4.3935 loss: 2.5161 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.5161 2023/02/17 23:39:46 - mmengine - INFO - Epoch(train) [6][ 40/1320] lr: 2.0000e-02 eta: 4:19:23 time: 0.2546 data_time: 0.0111 memory: 13708 grad_norm: 4.4031 loss: 2.4219 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.4219 2023/02/17 23:39:51 - mmengine - INFO - Epoch(train) [6][ 60/1320] lr: 2.0000e-02 eta: 4:19:17 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.3766 loss: 2.4868 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.4868 2023/02/17 23:39:56 - mmengine - INFO - Epoch(train) [6][ 80/1320] lr: 2.0000e-02 eta: 4:19:10 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.4628 loss: 2.3826 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.3826 2023/02/17 23:40:01 - mmengine - INFO - Epoch(train) [6][ 100/1320] lr: 2.0000e-02 eta: 4:19:04 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 4.3795 loss: 2.6224 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.6224 2023/02/17 23:40:06 - mmengine - INFO - Epoch(train) [6][ 120/1320] lr: 2.0000e-02 eta: 4:18:57 time: 0.2550 data_time: 0.0110 memory: 13708 grad_norm: 4.3842 loss: 2.6873 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.6873 2023/02/17 23:40:12 - mmengine - INFO - Epoch(train) [6][ 140/1320] lr: 2.0000e-02 eta: 4:18:51 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.4970 loss: 2.5677 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.5677 2023/02/17 23:40:17 - mmengine - INFO - Epoch(train) [6][ 160/1320] lr: 2.0000e-02 eta: 4:18:44 time: 0.2554 data_time: 0.0111 memory: 13708 grad_norm: 4.4497 loss: 2.5380 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.5380 2023/02/17 23:40:22 - mmengine - INFO - Epoch(train) [6][ 180/1320] lr: 2.0000e-02 eta: 4:18:38 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 4.3124 loss: 2.6797 top1_acc: 0.3125 top5_acc: 0.3750 loss_cls: 2.6797 2023/02/17 23:40:27 - mmengine - INFO - Epoch(train) [6][ 200/1320] lr: 2.0000e-02 eta: 4:18:31 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 4.2676 loss: 2.5227 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.5227 2023/02/17 23:40:32 - mmengine - INFO - Epoch(train) [6][ 220/1320] lr: 2.0000e-02 eta: 4:18:25 time: 0.2547 data_time: 0.0109 memory: 13708 grad_norm: 4.3727 loss: 2.5360 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.5360 2023/02/17 23:40:37 - mmengine - INFO - Epoch(train) [6][ 240/1320] lr: 2.0000e-02 eta: 4:18:19 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 4.3522 loss: 2.5067 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.5067 2023/02/17 23:40:42 - mmengine - INFO - Epoch(train) [6][ 260/1320] lr: 2.0000e-02 eta: 4:18:12 time: 0.2547 data_time: 0.0109 memory: 13708 grad_norm: 4.3799 loss: 2.4303 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.4303 2023/02/17 23:40:47 - mmengine - INFO - Epoch(train) [6][ 280/1320] lr: 2.0000e-02 eta: 4:18:06 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.3898 loss: 2.5219 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.5219 2023/02/17 23:40:52 - mmengine - INFO - Epoch(train) [6][ 300/1320] lr: 2.0000e-02 eta: 4:17:59 time: 0.2552 data_time: 0.0110 memory: 13708 grad_norm: 4.3518 loss: 2.4161 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.4161 2023/02/17 23:40:57 - mmengine - INFO - Epoch(train) [6][ 320/1320] lr: 2.0000e-02 eta: 4:17:53 time: 0.2548 data_time: 0.0109 memory: 13708 grad_norm: 4.2139 loss: 2.2640 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.2640 2023/02/17 23:41:03 - mmengine - INFO - Epoch(train) [6][ 340/1320] lr: 2.0000e-02 eta: 4:17:46 time: 0.2544 data_time: 0.0108 memory: 13708 grad_norm: 4.2983 loss: 2.4067 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.4067 2023/02/17 23:41:08 - mmengine - INFO - Epoch(train) [6][ 360/1320] lr: 2.0000e-02 eta: 4:17:40 time: 0.2550 data_time: 0.0112 memory: 13708 grad_norm: 4.4016 loss: 2.5720 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.5720 2023/02/17 23:41:13 - mmengine - INFO - Epoch(train) [6][ 380/1320] lr: 2.0000e-02 eta: 4:17:34 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.2860 loss: 2.3115 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.3115 2023/02/17 23:41:18 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:41:18 - mmengine - INFO - Epoch(train) [6][ 400/1320] lr: 2.0000e-02 eta: 4:17:27 time: 0.2560 data_time: 0.0117 memory: 13708 grad_norm: 4.4131 loss: 2.4721 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.4721 2023/02/17 23:41:23 - mmengine - INFO - Epoch(train) [6][ 420/1320] lr: 2.0000e-02 eta: 4:17:21 time: 0.2550 data_time: 0.0114 memory: 13708 grad_norm: 4.5459 loss: 2.4068 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.4068 2023/02/17 23:41:28 - mmengine - INFO - Epoch(train) [6][ 440/1320] lr: 2.0000e-02 eta: 4:17:15 time: 0.2548 data_time: 0.0111 memory: 13708 grad_norm: 4.3480 loss: 2.4243 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.4243 2023/02/17 23:41:33 - mmengine - INFO - Epoch(train) [6][ 460/1320] lr: 2.0000e-02 eta: 4:17:08 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 4.3600 loss: 2.5944 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.5944 2023/02/17 23:41:38 - mmengine - INFO - Epoch(train) [6][ 480/1320] lr: 2.0000e-02 eta: 4:17:02 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 4.4347 loss: 2.3169 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.3169 2023/02/17 23:41:43 - mmengine - INFO - Epoch(train) [6][ 500/1320] lr: 2.0000e-02 eta: 4:16:56 time: 0.2554 data_time: 0.0111 memory: 13708 grad_norm: 4.3851 loss: 2.5792 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.5792 2023/02/17 23:41:49 - mmengine - INFO - Epoch(train) [6][ 520/1320] lr: 2.0000e-02 eta: 4:16:49 time: 0.2548 data_time: 0.0112 memory: 13708 grad_norm: 4.3820 loss: 2.5372 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.5372 2023/02/17 23:41:54 - mmengine - INFO - Epoch(train) [6][ 540/1320] lr: 2.0000e-02 eta: 4:16:43 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 4.1642 loss: 2.3476 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.3476 2023/02/17 23:41:59 - mmengine - INFO - Epoch(train) [6][ 560/1320] lr: 2.0000e-02 eta: 4:16:37 time: 0.2553 data_time: 0.0112 memory: 13708 grad_norm: 4.4703 loss: 2.3230 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.3230 2023/02/17 23:42:04 - mmengine - INFO - Epoch(train) [6][ 580/1320] lr: 2.0000e-02 eta: 4:16:30 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.3336 loss: 2.8203 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.8203 2023/02/17 23:42:09 - mmengine - INFO - Epoch(train) [6][ 600/1320] lr: 2.0000e-02 eta: 4:16:24 time: 0.2554 data_time: 0.0112 memory: 13708 grad_norm: 4.4216 loss: 2.5305 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.5305 2023/02/17 23:42:14 - mmengine - INFO - Epoch(train) [6][ 620/1320] lr: 2.0000e-02 eta: 4:16:18 time: 0.2557 data_time: 0.0120 memory: 13708 grad_norm: 4.3430 loss: 2.4569 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.4569 2023/02/17 23:42:19 - mmengine - INFO - Epoch(train) [6][ 640/1320] lr: 2.0000e-02 eta: 4:16:12 time: 0.2549 data_time: 0.0112 memory: 13708 grad_norm: 4.4226 loss: 2.4627 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.4627 2023/02/17 23:42:24 - mmengine - INFO - Epoch(train) [6][ 660/1320] lr: 2.0000e-02 eta: 4:16:05 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.3833 loss: 2.4760 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.4760 2023/02/17 23:42:29 - mmengine - INFO - Epoch(train) [6][ 680/1320] lr: 2.0000e-02 eta: 4:15:59 time: 0.2546 data_time: 0.0108 memory: 13708 grad_norm: 4.2284 loss: 2.3638 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.3638 2023/02/17 23:42:34 - mmengine - INFO - Epoch(train) [6][ 700/1320] lr: 2.0000e-02 eta: 4:15:53 time: 0.2543 data_time: 0.0105 memory: 13708 grad_norm: 4.4048 loss: 2.5692 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.5692 2023/02/17 23:42:40 - mmengine - INFO - Epoch(train) [6][ 720/1320] lr: 2.0000e-02 eta: 4:15:46 time: 0.2545 data_time: 0.0106 memory: 13708 grad_norm: 4.4997 loss: 2.3580 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.3580 2023/02/17 23:42:45 - mmengine - INFO - Epoch(train) [6][ 740/1320] lr: 2.0000e-02 eta: 4:15:40 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 4.3133 loss: 2.7299 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.7299 2023/02/17 23:42:50 - mmengine - INFO - Epoch(train) [6][ 760/1320] lr: 2.0000e-02 eta: 4:15:34 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 4.3498 loss: 2.5614 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.5614 2023/02/17 23:42:55 - mmengine - INFO - Epoch(train) [6][ 780/1320] lr: 2.0000e-02 eta: 4:15:28 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 4.2157 loss: 2.3211 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.3211 2023/02/17 23:43:00 - mmengine - INFO - Epoch(train) [6][ 800/1320] lr: 2.0000e-02 eta: 4:15:21 time: 0.2549 data_time: 0.0108 memory: 13708 grad_norm: 4.2779 loss: 2.4171 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.4171 2023/02/17 23:43:05 - mmengine - INFO - Epoch(train) [6][ 820/1320] lr: 2.0000e-02 eta: 4:15:15 time: 0.2543 data_time: 0.0106 memory: 13708 grad_norm: 4.3500 loss: 2.4391 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.4391 2023/02/17 23:43:10 - mmengine - INFO - Epoch(train) [6][ 840/1320] lr: 2.0000e-02 eta: 4:15:09 time: 0.2545 data_time: 0.0107 memory: 13708 grad_norm: 4.2289 loss: 2.2581 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.2581 2023/02/17 23:43:15 - mmengine - INFO - Epoch(train) [6][ 860/1320] lr: 2.0000e-02 eta: 4:15:03 time: 0.2560 data_time: 0.0111 memory: 13708 grad_norm: 4.3332 loss: 2.4794 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.4794 2023/02/17 23:43:20 - mmengine - INFO - Epoch(train) [6][ 880/1320] lr: 2.0000e-02 eta: 4:14:56 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 4.3742 loss: 2.1799 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1799 2023/02/17 23:43:25 - mmengine - INFO - Epoch(train) [6][ 900/1320] lr: 2.0000e-02 eta: 4:14:50 time: 0.2555 data_time: 0.0110 memory: 13708 grad_norm: 4.3248 loss: 2.3093 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.3093 2023/02/17 23:43:31 - mmengine - INFO - Epoch(train) [6][ 920/1320] lr: 2.0000e-02 eta: 4:14:44 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.2020 loss: 2.5283 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.5283 2023/02/17 23:43:36 - mmengine - INFO - Epoch(train) [6][ 940/1320] lr: 2.0000e-02 eta: 4:14:38 time: 0.2550 data_time: 0.0112 memory: 13708 grad_norm: 4.3204 loss: 2.4500 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.4500 2023/02/17 23:43:41 - mmengine - INFO - Epoch(train) [6][ 960/1320] lr: 2.0000e-02 eta: 4:14:32 time: 0.2556 data_time: 0.0114 memory: 13708 grad_norm: 4.3501 loss: 2.5713 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.5713 2023/02/17 23:43:46 - mmengine - INFO - Epoch(train) [6][ 980/1320] lr: 2.0000e-02 eta: 4:14:26 time: 0.2550 data_time: 0.0110 memory: 13708 grad_norm: 4.2034 loss: 2.4477 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.4477 2023/02/17 23:43:51 - mmengine - INFO - Epoch(train) [6][1000/1320] lr: 2.0000e-02 eta: 4:14:19 time: 0.2548 data_time: 0.0112 memory: 13708 grad_norm: 4.3017 loss: 2.3498 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.3498 2023/02/17 23:43:56 - mmengine - INFO - Epoch(train) [6][1020/1320] lr: 2.0000e-02 eta: 4:14:13 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 4.3140 loss: 2.4594 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.4594 2023/02/17 23:44:01 - mmengine - INFO - Epoch(train) [6][1040/1320] lr: 2.0000e-02 eta: 4:14:07 time: 0.2547 data_time: 0.0109 memory: 13708 grad_norm: 4.2584 loss: 2.4249 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.4249 2023/02/17 23:44:06 - mmengine - INFO - Epoch(train) [6][1060/1320] lr: 2.0000e-02 eta: 4:14:01 time: 0.2564 data_time: 0.0113 memory: 13708 grad_norm: 4.2328 loss: 2.3470 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 2.3470 2023/02/17 23:44:11 - mmengine - INFO - Epoch(train) [6][1080/1320] lr: 2.0000e-02 eta: 4:13:55 time: 0.2554 data_time: 0.0112 memory: 13708 grad_norm: 4.3778 loss: 2.3710 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.3710 2023/02/17 23:44:17 - mmengine - INFO - Epoch(train) [6][1100/1320] lr: 2.0000e-02 eta: 4:13:49 time: 0.2547 data_time: 0.0103 memory: 13708 grad_norm: 4.3204 loss: 2.3776 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.3776 2023/02/17 23:44:22 - mmengine - INFO - Epoch(train) [6][1120/1320] lr: 2.0000e-02 eta: 4:13:42 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.2700 loss: 2.5906 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.5906 2023/02/17 23:44:27 - mmengine - INFO - Epoch(train) [6][1140/1320] lr: 2.0000e-02 eta: 4:13:36 time: 0.2542 data_time: 0.0099 memory: 13708 grad_norm: 4.1899 loss: 2.3692 top1_acc: 0.6875 top5_acc: 0.6875 loss_cls: 2.3692 2023/02/17 23:44:32 - mmengine - INFO - Epoch(train) [6][1160/1320] lr: 2.0000e-02 eta: 4:13:30 time: 0.2541 data_time: 0.0098 memory: 13708 grad_norm: 4.3340 loss: 2.2727 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.2727 2023/02/17 23:44:37 - mmengine - INFO - Epoch(train) [6][1180/1320] lr: 2.0000e-02 eta: 4:13:24 time: 0.2540 data_time: 0.0096 memory: 13708 grad_norm: 4.4073 loss: 2.5415 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.5415 2023/02/17 23:44:42 - mmengine - INFO - Epoch(train) [6][1200/1320] lr: 2.0000e-02 eta: 4:13:17 time: 0.2551 data_time: 0.0100 memory: 13708 grad_norm: 4.3113 loss: 2.6129 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.6129 2023/02/17 23:44:47 - mmengine - INFO - Epoch(train) [6][1220/1320] lr: 2.0000e-02 eta: 4:13:11 time: 0.2548 data_time: 0.0100 memory: 13708 grad_norm: 4.2691 loss: 2.4814 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.4814 2023/02/17 23:44:52 - mmengine - INFO - Epoch(train) [6][1240/1320] lr: 2.0000e-02 eta: 4:13:05 time: 0.2560 data_time: 0.0099 memory: 13708 grad_norm: 4.2739 loss: 2.2918 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.2918 2023/02/17 23:44:57 - mmengine - INFO - Epoch(train) [6][1260/1320] lr: 2.0000e-02 eta: 4:12:59 time: 0.2541 data_time: 0.0099 memory: 13708 grad_norm: 4.4349 loss: 2.4702 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.4702 2023/02/17 23:45:02 - mmengine - INFO - Epoch(train) [6][1280/1320] lr: 2.0000e-02 eta: 4:12:53 time: 0.2546 data_time: 0.0106 memory: 13708 grad_norm: 4.2627 loss: 2.4023 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.4023 2023/02/17 23:45:07 - mmengine - INFO - Epoch(train) [6][1300/1320] lr: 2.0000e-02 eta: 4:12:47 time: 0.2540 data_time: 0.0102 memory: 13708 grad_norm: 4.3316 loss: 2.2982 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.2982 2023/02/17 23:45:12 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:45:12 - mmengine - INFO - Epoch(train) [6][1320/1320] lr: 2.0000e-02 eta: 4:12:40 time: 0.2496 data_time: 0.0099 memory: 13708 grad_norm: 4.3650 loss: 2.5429 top1_acc: 0.6364 top5_acc: 0.8182 loss_cls: 2.5429 2023/02/17 23:45:12 - mmengine - INFO - Saving checkpoint at 6 epochs 2023/02/17 23:45:16 - mmengine - INFO - Epoch(val) [6][ 20/194] eta: 0:00:21 time: 0.1240 data_time: 0.0552 memory: 1818 2023/02/17 23:45:18 - mmengine - INFO - Epoch(val) [6][ 40/194] eta: 0:00:16 time: 0.0881 data_time: 0.0199 memory: 1818 2023/02/17 23:45:19 - mmengine - INFO - Epoch(val) [6][ 60/194] eta: 0:00:13 time: 0.0858 data_time: 0.0184 memory: 1818 2023/02/17 23:45:21 - mmengine - INFO - Epoch(val) [6][ 80/194] eta: 0:00:10 time: 0.0856 data_time: 0.0170 memory: 1818 2023/02/17 23:45:23 - mmengine - INFO - Epoch(val) [6][100/194] eta: 0:00:08 time: 0.0918 data_time: 0.0239 memory: 1818 2023/02/17 23:45:25 - mmengine - INFO - Epoch(val) [6][120/194] eta: 0:00:06 time: 0.0919 data_time: 0.0243 memory: 1818 2023/02/17 23:45:26 - mmengine - INFO - Epoch(val) [6][140/194] eta: 0:00:05 time: 0.0822 data_time: 0.0145 memory: 1818 2023/02/17 23:45:28 - mmengine - INFO - Epoch(val) [6][160/194] eta: 0:00:03 time: 0.0802 data_time: 0.0126 memory: 1818 2023/02/17 23:45:30 - mmengine - INFO - Epoch(val) [6][180/194] eta: 0:00:01 time: 0.0822 data_time: 0.0159 memory: 1818 2023/02/17 23:45:31 - mmengine - INFO - Epoch(val) [6][194/194] acc/top1: 0.3802 acc/top5: 0.6809 acc/mean1: 0.3261 2023/02/17 23:45:31 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_4.pth is removed 2023/02/17 23:45:32 - mmengine - INFO - The best checkpoint with 0.3802 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2023/02/17 23:45:38 - mmengine - INFO - Epoch(train) [7][ 20/1320] lr: 2.0000e-02 eta: 4:12:40 time: 0.2962 data_time: 0.0420 memory: 13708 grad_norm: 4.3158 loss: 2.2527 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2527 2023/02/17 23:45:43 - mmengine - INFO - Epoch(train) [7][ 40/1320] lr: 2.0000e-02 eta: 4:12:34 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 4.1879 loss: 2.2691 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2691 2023/02/17 23:45:48 - mmengine - INFO - Epoch(train) [7][ 60/1320] lr: 2.0000e-02 eta: 4:12:28 time: 0.2560 data_time: 0.0120 memory: 13708 grad_norm: 4.3136 loss: 2.4420 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.4420 2023/02/17 23:45:53 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:45:53 - mmengine - INFO - Epoch(train) [7][ 80/1320] lr: 2.0000e-02 eta: 4:12:22 time: 0.2554 data_time: 0.0111 memory: 13708 grad_norm: 4.3850 loss: 2.3947 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.3947 2023/02/17 23:45:59 - mmengine - INFO - Epoch(train) [7][ 100/1320] lr: 2.0000e-02 eta: 4:12:15 time: 0.2549 data_time: 0.0108 memory: 13708 grad_norm: 4.3168 loss: 2.4762 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.4762 2023/02/17 23:46:04 - mmengine - INFO - Epoch(train) [7][ 120/1320] lr: 2.0000e-02 eta: 4:12:09 time: 0.2552 data_time: 0.0113 memory: 13708 grad_norm: 4.4642 loss: 2.3522 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.3522 2023/02/17 23:46:09 - mmengine - INFO - Epoch(train) [7][ 140/1320] lr: 2.0000e-02 eta: 4:12:04 time: 0.2587 data_time: 0.0133 memory: 13708 grad_norm: 4.3506 loss: 2.4475 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 2.4475 2023/02/17 23:46:14 - mmengine - INFO - Epoch(train) [7][ 160/1320] lr: 2.0000e-02 eta: 4:11:58 time: 0.2570 data_time: 0.0128 memory: 13708 grad_norm: 4.3057 loss: 2.4484 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.4484 2023/02/17 23:46:19 - mmengine - INFO - Epoch(train) [7][ 180/1320] lr: 2.0000e-02 eta: 4:11:52 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.2183 loss: 2.5544 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.5544 2023/02/17 23:46:24 - mmengine - INFO - Epoch(train) [7][ 200/1320] lr: 2.0000e-02 eta: 4:11:46 time: 0.2545 data_time: 0.0108 memory: 13708 grad_norm: 4.3478 loss: 2.4574 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.4574 2023/02/17 23:46:29 - mmengine - INFO - Epoch(train) [7][ 220/1320] lr: 2.0000e-02 eta: 4:11:40 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.3546 loss: 2.3307 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.3307 2023/02/17 23:46:34 - mmengine - INFO - Epoch(train) [7][ 240/1320] lr: 2.0000e-02 eta: 4:11:34 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.3524 loss: 2.1344 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1344 2023/02/17 23:46:40 - mmengine - INFO - Epoch(train) [7][ 260/1320] lr: 2.0000e-02 eta: 4:11:28 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.2501 loss: 2.4615 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.4615 2023/02/17 23:46:45 - mmengine - INFO - Epoch(train) [7][ 280/1320] lr: 2.0000e-02 eta: 4:11:22 time: 0.2557 data_time: 0.0111 memory: 13708 grad_norm: 4.3679 loss: 2.2942 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.2942 2023/02/17 23:46:50 - mmengine - INFO - Epoch(train) [7][ 300/1320] lr: 2.0000e-02 eta: 4:11:16 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 4.2796 loss: 2.4966 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.4966 2023/02/17 23:46:55 - mmengine - INFO - Epoch(train) [7][ 320/1320] lr: 2.0000e-02 eta: 4:11:10 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.2353 loss: 2.2163 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.2163 2023/02/17 23:47:00 - mmengine - INFO - Epoch(train) [7][ 340/1320] lr: 2.0000e-02 eta: 4:11:03 time: 0.2545 data_time: 0.0106 memory: 13708 grad_norm: 4.2149 loss: 2.6709 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.6709 2023/02/17 23:47:05 - mmengine - INFO - Epoch(train) [7][ 360/1320] lr: 2.0000e-02 eta: 4:10:58 time: 0.2557 data_time: 0.0114 memory: 13708 grad_norm: 4.3565 loss: 2.3137 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.3137 2023/02/17 23:47:10 - mmengine - INFO - Epoch(train) [7][ 380/1320] lr: 2.0000e-02 eta: 4:10:51 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.2633 loss: 2.4038 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.4038 2023/02/17 23:47:15 - mmengine - INFO - Epoch(train) [7][ 400/1320] lr: 2.0000e-02 eta: 4:10:45 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 4.3266 loss: 2.4155 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.4155 2023/02/17 23:47:20 - mmengine - INFO - Epoch(train) [7][ 420/1320] lr: 2.0000e-02 eta: 4:10:39 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 4.2581 loss: 2.3142 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.3142 2023/02/17 23:47:25 - mmengine - INFO - Epoch(train) [7][ 440/1320] lr: 2.0000e-02 eta: 4:10:34 time: 0.2557 data_time: 0.0111 memory: 13708 grad_norm: 4.4507 loss: 2.4843 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 2.4843 2023/02/17 23:47:31 - mmengine - INFO - Epoch(train) [7][ 460/1320] lr: 2.0000e-02 eta: 4:10:28 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.2967 loss: 2.4271 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.4271 2023/02/17 23:47:36 - mmengine - INFO - Epoch(train) [7][ 480/1320] lr: 2.0000e-02 eta: 4:10:22 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 4.3324 loss: 2.3361 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.3361 2023/02/17 23:47:41 - mmengine - INFO - Epoch(train) [7][ 500/1320] lr: 2.0000e-02 eta: 4:10:16 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.2911 loss: 2.1729 top1_acc: 0.2500 top5_acc: 0.8750 loss_cls: 2.1729 2023/02/17 23:47:46 - mmengine - INFO - Epoch(train) [7][ 520/1320] lr: 2.0000e-02 eta: 4:10:09 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.2901 loss: 2.4096 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.4096 2023/02/17 23:47:51 - mmengine - INFO - Epoch(train) [7][ 540/1320] lr: 2.0000e-02 eta: 4:10:04 time: 0.2552 data_time: 0.0110 memory: 13708 grad_norm: 4.3127 loss: 2.5352 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.5352 2023/02/17 23:47:56 - mmengine - INFO - Epoch(train) [7][ 560/1320] lr: 2.0000e-02 eta: 4:09:58 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.2884 loss: 2.5061 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.5061 2023/02/17 23:48:01 - mmengine - INFO - Epoch(train) [7][ 580/1320] lr: 2.0000e-02 eta: 4:09:52 time: 0.2549 data_time: 0.0111 memory: 13708 grad_norm: 4.2506 loss: 2.3725 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.3725 2023/02/17 23:48:06 - mmengine - INFO - Epoch(train) [7][ 600/1320] lr: 2.0000e-02 eta: 4:09:46 time: 0.2574 data_time: 0.0126 memory: 13708 grad_norm: 4.2364 loss: 2.3083 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.3083 2023/02/17 23:48:11 - mmengine - INFO - Epoch(train) [7][ 620/1320] lr: 2.0000e-02 eta: 4:09:40 time: 0.2585 data_time: 0.0126 memory: 13708 grad_norm: 4.2667 loss: 2.0825 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.0825 2023/02/17 23:48:17 - mmengine - INFO - Epoch(train) [7][ 640/1320] lr: 2.0000e-02 eta: 4:09:34 time: 0.2559 data_time: 0.0113 memory: 13708 grad_norm: 4.2758 loss: 2.4745 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.4745 2023/02/17 23:48:22 - mmengine - INFO - Epoch(train) [7][ 660/1320] lr: 2.0000e-02 eta: 4:09:29 time: 0.2553 data_time: 0.0112 memory: 13708 grad_norm: 4.2222 loss: 2.5143 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.5143 2023/02/17 23:48:27 - mmengine - INFO - Epoch(train) [7][ 680/1320] lr: 2.0000e-02 eta: 4:09:23 time: 0.2546 data_time: 0.0107 memory: 13708 grad_norm: 4.3683 loss: 2.2146 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.2146 2023/02/17 23:48:32 - mmengine - INFO - Epoch(train) [7][ 700/1320] lr: 2.0000e-02 eta: 4:09:17 time: 0.2553 data_time: 0.0111 memory: 13708 grad_norm: 4.3372 loss: 2.1928 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1928 2023/02/17 23:48:37 - mmengine - INFO - Epoch(train) [7][ 720/1320] lr: 2.0000e-02 eta: 4:09:11 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.4046 loss: 2.4297 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.4297 2023/02/17 23:48:42 - mmengine - INFO - Epoch(train) [7][ 740/1320] lr: 2.0000e-02 eta: 4:09:05 time: 0.2546 data_time: 0.0110 memory: 13708 grad_norm: 4.3163 loss: 2.3262 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.3262 2023/02/17 23:48:47 - mmengine - INFO - Epoch(train) [7][ 760/1320] lr: 2.0000e-02 eta: 4:08:59 time: 0.2553 data_time: 0.0113 memory: 13708 grad_norm: 4.2773 loss: 2.2077 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.2077 2023/02/17 23:48:52 - mmengine - INFO - Epoch(train) [7][ 780/1320] lr: 2.0000e-02 eta: 4:08:53 time: 0.2550 data_time: 0.0110 memory: 13708 grad_norm: 4.3729 loss: 2.4164 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.4164 2023/02/17 23:48:57 - mmengine - INFO - Epoch(train) [7][ 800/1320] lr: 2.0000e-02 eta: 4:08:47 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 4.3976 loss: 2.4148 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 2.4148 2023/02/17 23:49:03 - mmengine - INFO - Epoch(train) [7][ 820/1320] lr: 2.0000e-02 eta: 4:08:41 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.1787 loss: 2.3102 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.3102 2023/02/17 23:49:08 - mmengine - INFO - Epoch(train) [7][ 840/1320] lr: 2.0000e-02 eta: 4:08:35 time: 0.2557 data_time: 0.0117 memory: 13708 grad_norm: 4.1375 loss: 2.4545 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.4545 2023/02/17 23:49:13 - mmengine - INFO - Epoch(train) [7][ 860/1320] lr: 2.0000e-02 eta: 4:08:29 time: 0.2557 data_time: 0.0112 memory: 13708 grad_norm: 4.2245 loss: 2.3470 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3470 2023/02/17 23:49:18 - mmengine - INFO - Epoch(train) [7][ 880/1320] lr: 2.0000e-02 eta: 4:08:23 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 4.4456 loss: 2.5637 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.5637 2023/02/17 23:49:23 - mmengine - INFO - Epoch(train) [7][ 900/1320] lr: 2.0000e-02 eta: 4:08:18 time: 0.2564 data_time: 0.0106 memory: 13708 grad_norm: 4.2556 loss: 2.1846 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.1846 2023/02/17 23:49:28 - mmengine - INFO - Epoch(train) [7][ 920/1320] lr: 2.0000e-02 eta: 4:08:12 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.2561 loss: 2.2625 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.2625 2023/02/17 23:49:33 - mmengine - INFO - Epoch(train) [7][ 940/1320] lr: 2.0000e-02 eta: 4:08:06 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.2425 loss: 2.2430 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.2430 2023/02/17 23:49:38 - mmengine - INFO - Epoch(train) [7][ 960/1320] lr: 2.0000e-02 eta: 4:08:00 time: 0.2557 data_time: 0.0112 memory: 13708 grad_norm: 4.3390 loss: 2.5183 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.5183 2023/02/17 23:49:43 - mmengine - INFO - Epoch(train) [7][ 980/1320] lr: 2.0000e-02 eta: 4:07:54 time: 0.2550 data_time: 0.0111 memory: 13708 grad_norm: 4.2717 loss: 2.3262 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.3262 2023/02/17 23:49:49 - mmengine - INFO - Epoch(train) [7][1000/1320] lr: 2.0000e-02 eta: 4:07:48 time: 0.2550 data_time: 0.0110 memory: 13708 grad_norm: 4.1536 loss: 2.5426 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 2.5426 2023/02/17 23:49:54 - mmengine - INFO - Epoch(train) [7][1020/1320] lr: 2.0000e-02 eta: 4:07:42 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.2083 loss: 2.3635 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.3635 2023/02/17 23:49:59 - mmengine - INFO - Epoch(train) [7][1040/1320] lr: 2.0000e-02 eta: 4:07:36 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.2192 loss: 2.2379 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.2379 2023/02/17 23:50:04 - mmengine - INFO - Epoch(train) [7][1060/1320] lr: 2.0000e-02 eta: 4:07:31 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.4902 loss: 2.2444 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.2444 2023/02/17 23:50:09 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:50:09 - mmengine - INFO - Epoch(train) [7][1080/1320] lr: 2.0000e-02 eta: 4:07:25 time: 0.2574 data_time: 0.0127 memory: 13708 grad_norm: 4.4517 loss: 2.2878 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2878 2023/02/17 23:50:14 - mmengine - INFO - Epoch(train) [7][1100/1320] lr: 2.0000e-02 eta: 4:07:19 time: 0.2540 data_time: 0.0102 memory: 13708 grad_norm: 4.3346 loss: 2.4329 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.4329 2023/02/17 23:50:19 - mmengine - INFO - Epoch(train) [7][1120/1320] lr: 2.0000e-02 eta: 4:07:13 time: 0.2546 data_time: 0.0099 memory: 13708 grad_norm: 4.3544 loss: 2.2479 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 2.2479 2023/02/17 23:50:24 - mmengine - INFO - Epoch(train) [7][1140/1320] lr: 2.0000e-02 eta: 4:07:07 time: 0.2549 data_time: 0.0098 memory: 13708 grad_norm: 4.4111 loss: 2.2403 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.2403 2023/02/17 23:50:29 - mmengine - INFO - Epoch(train) [7][1160/1320] lr: 2.0000e-02 eta: 4:07:01 time: 0.2542 data_time: 0.0098 memory: 13708 grad_norm: 4.3645 loss: 2.3107 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 2.3107 2023/02/17 23:50:34 - mmengine - INFO - Epoch(train) [7][1180/1320] lr: 2.0000e-02 eta: 4:06:55 time: 0.2540 data_time: 0.0098 memory: 13708 grad_norm: 4.4535 loss: 2.6658 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.6658 2023/02/17 23:50:40 - mmengine - INFO - Epoch(train) [7][1200/1320] lr: 2.0000e-02 eta: 4:06:49 time: 0.2550 data_time: 0.0100 memory: 13708 grad_norm: 4.1689 loss: 2.2075 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.2075 2023/02/17 23:50:45 - mmengine - INFO - Epoch(train) [7][1220/1320] lr: 2.0000e-02 eta: 4:06:43 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.3662 loss: 2.3214 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.3214 2023/02/17 23:50:50 - mmengine - INFO - Epoch(train) [7][1240/1320] lr: 2.0000e-02 eta: 4:06:37 time: 0.2541 data_time: 0.0100 memory: 13708 grad_norm: 4.3184 loss: 2.4029 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.4029 2023/02/17 23:50:55 - mmengine - INFO - Epoch(train) [7][1260/1320] lr: 2.0000e-02 eta: 4:06:31 time: 0.2542 data_time: 0.0101 memory: 13708 grad_norm: 4.3976 loss: 2.2752 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.2752 2023/02/17 23:51:00 - mmengine - INFO - Epoch(train) [7][1280/1320] lr: 2.0000e-02 eta: 4:06:26 time: 0.2548 data_time: 0.0100 memory: 13708 grad_norm: 4.3700 loss: 2.3930 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.3930 2023/02/17 23:51:05 - mmengine - INFO - Epoch(train) [7][1300/1320] lr: 2.0000e-02 eta: 4:06:20 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.1912 loss: 2.5712 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.5712 2023/02/17 23:51:10 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:51:10 - mmengine - INFO - Epoch(train) [7][1320/1320] lr: 2.0000e-02 eta: 4:06:13 time: 0.2494 data_time: 0.0097 memory: 13708 grad_norm: 4.3998 loss: 2.2571 top1_acc: 0.3636 top5_acc: 0.8182 loss_cls: 2.2571 2023/02/17 23:51:13 - mmengine - INFO - Epoch(val) [7][ 20/194] eta: 0:00:21 time: 0.1259 data_time: 0.0584 memory: 1818 2023/02/17 23:51:14 - mmengine - INFO - Epoch(val) [7][ 40/194] eta: 0:00:16 time: 0.0868 data_time: 0.0197 memory: 1818 2023/02/17 23:51:16 - mmengine - INFO - Epoch(val) [7][ 60/194] eta: 0:00:13 time: 0.0868 data_time: 0.0193 memory: 1818 2023/02/17 23:51:18 - mmengine - INFO - Epoch(val) [7][ 80/194] eta: 0:00:10 time: 0.0837 data_time: 0.0166 memory: 1818 2023/02/17 23:51:19 - mmengine - INFO - Epoch(val) [7][100/194] eta: 0:00:08 time: 0.0895 data_time: 0.0220 memory: 1818 2023/02/17 23:51:21 - mmengine - INFO - Epoch(val) [7][120/194] eta: 0:00:06 time: 0.0833 data_time: 0.0158 memory: 1818 2023/02/17 23:51:23 - mmengine - INFO - Epoch(val) [7][140/194] eta: 0:00:04 time: 0.0882 data_time: 0.0203 memory: 1818 2023/02/17 23:51:25 - mmengine - INFO - Epoch(val) [7][160/194] eta: 0:00:03 time: 0.0809 data_time: 0.0137 memory: 1818 2023/02/17 23:51:26 - mmengine - INFO - Epoch(val) [7][180/194] eta: 0:00:01 time: 0.0890 data_time: 0.0205 memory: 1818 2023/02/17 23:51:29 - mmengine - INFO - Epoch(val) [7][194/194] acc/top1: 0.3857 acc/top5: 0.6980 acc/mean1: 0.3284 2023/02/17 23:51:29 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_6.pth is removed 2023/02/17 23:51:29 - mmengine - INFO - The best checkpoint with 0.3857 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2023/02/17 23:51:35 - mmengine - INFO - Epoch(train) [8][ 20/1320] lr: 2.0000e-02 eta: 4:06:12 time: 0.2936 data_time: 0.0419 memory: 13708 grad_norm: 4.2252 loss: 2.4632 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.4632 2023/02/17 23:51:40 - mmengine - INFO - Epoch(train) [8][ 40/1320] lr: 2.0000e-02 eta: 4:06:06 time: 0.2559 data_time: 0.0115 memory: 13708 grad_norm: 4.2730 loss: 2.2033 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.2033 2023/02/17 23:51:46 - mmengine - INFO - Epoch(train) [8][ 60/1320] lr: 2.0000e-02 eta: 4:06:00 time: 0.2552 data_time: 0.0111 memory: 13708 grad_norm: 4.3182 loss: 2.1302 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.1302 2023/02/17 23:51:51 - mmengine - INFO - Epoch(train) [8][ 80/1320] lr: 2.0000e-02 eta: 4:05:55 time: 0.2552 data_time: 0.0111 memory: 13708 grad_norm: 4.4834 loss: 2.3313 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 2.3313 2023/02/17 23:51:56 - mmengine - INFO - Epoch(train) [8][ 100/1320] lr: 2.0000e-02 eta: 4:05:49 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 4.2976 loss: 2.1938 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1938 2023/02/17 23:52:01 - mmengine - INFO - Epoch(train) [8][ 120/1320] lr: 2.0000e-02 eta: 4:05:43 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 4.3981 loss: 2.4081 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.4081 2023/02/17 23:52:06 - mmengine - INFO - Epoch(train) [8][ 140/1320] lr: 2.0000e-02 eta: 4:05:37 time: 0.2550 data_time: 0.0112 memory: 13708 grad_norm: 4.2641 loss: 2.2570 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 2.2570 2023/02/17 23:52:11 - mmengine - INFO - Epoch(train) [8][ 160/1320] lr: 2.0000e-02 eta: 4:05:31 time: 0.2549 data_time: 0.0110 memory: 13708 grad_norm: 4.4322 loss: 2.2386 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.2386 2023/02/17 23:52:16 - mmengine - INFO - Epoch(train) [8][ 180/1320] lr: 2.0000e-02 eta: 4:05:26 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.3468 loss: 2.3167 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.3167 2023/02/17 23:52:21 - mmengine - INFO - Epoch(train) [8][ 200/1320] lr: 2.0000e-02 eta: 4:05:20 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.3336 loss: 2.2059 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.2059 2023/02/17 23:52:26 - mmengine - INFO - Epoch(train) [8][ 220/1320] lr: 2.0000e-02 eta: 4:05:14 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.3633 loss: 2.1781 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.1781 2023/02/17 23:52:32 - mmengine - INFO - Epoch(train) [8][ 240/1320] lr: 2.0000e-02 eta: 4:05:08 time: 0.2565 data_time: 0.0111 memory: 13708 grad_norm: 4.4052 loss: 2.2128 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.2128 2023/02/17 23:52:37 - mmengine - INFO - Epoch(train) [8][ 260/1320] lr: 2.0000e-02 eta: 4:05:02 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.3044 loss: 2.2149 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.2149 2023/02/17 23:52:42 - mmengine - INFO - Epoch(train) [8][ 280/1320] lr: 2.0000e-02 eta: 4:04:57 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.4444 loss: 2.3249 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3249 2023/02/17 23:52:47 - mmengine - INFO - Epoch(train) [8][ 300/1320] lr: 2.0000e-02 eta: 4:04:51 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 4.3699 loss: 2.3412 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.3412 2023/02/17 23:52:52 - mmengine - INFO - Epoch(train) [8][ 320/1320] lr: 2.0000e-02 eta: 4:04:45 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 4.4199 loss: 2.3650 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.3650 2023/02/17 23:52:57 - mmengine - INFO - Epoch(train) [8][ 340/1320] lr: 2.0000e-02 eta: 4:04:39 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 4.3380 loss: 2.1219 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.1219 2023/02/17 23:53:02 - mmengine - INFO - Epoch(train) [8][ 360/1320] lr: 2.0000e-02 eta: 4:04:34 time: 0.2544 data_time: 0.0103 memory: 13708 grad_norm: 4.2316 loss: 2.3191 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.3191 2023/02/17 23:53:07 - mmengine - INFO - Epoch(train) [8][ 380/1320] lr: 2.0000e-02 eta: 4:04:28 time: 0.2549 data_time: 0.0103 memory: 13708 grad_norm: 4.2596 loss: 2.3210 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.3210 2023/02/17 23:53:12 - mmengine - INFO - Epoch(train) [8][ 400/1320] lr: 2.0000e-02 eta: 4:04:22 time: 0.2544 data_time: 0.0103 memory: 13708 grad_norm: 4.2378 loss: 2.5103 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.5103 2023/02/17 23:53:17 - mmengine - INFO - Epoch(train) [8][ 420/1320] lr: 2.0000e-02 eta: 4:04:16 time: 0.2550 data_time: 0.0100 memory: 13708 grad_norm: 4.3736 loss: 2.3051 top1_acc: 0.3750 top5_acc: 0.4375 loss_cls: 2.3051 2023/02/17 23:53:23 - mmengine - INFO - Epoch(train) [8][ 440/1320] lr: 2.0000e-02 eta: 4:04:10 time: 0.2549 data_time: 0.0100 memory: 13708 grad_norm: 4.3372 loss: 2.4043 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.4043 2023/02/17 23:53:28 - mmengine - INFO - Epoch(train) [8][ 460/1320] lr: 2.0000e-02 eta: 4:04:04 time: 0.2542 data_time: 0.0099 memory: 13708 grad_norm: 4.3045 loss: 2.2317 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.2317 2023/02/17 23:53:33 - mmengine - INFO - Epoch(train) [8][ 480/1320] lr: 2.0000e-02 eta: 4:03:59 time: 0.2546 data_time: 0.0101 memory: 13708 grad_norm: 4.3606 loss: 2.2002 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.2002 2023/02/17 23:53:38 - mmengine - INFO - Epoch(train) [8][ 500/1320] lr: 2.0000e-02 eta: 4:03:53 time: 0.2555 data_time: 0.0106 memory: 13708 grad_norm: 4.4919 loss: 2.4589 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.4589 2023/02/17 23:53:43 - mmengine - INFO - Epoch(train) [8][ 520/1320] lr: 2.0000e-02 eta: 4:03:47 time: 0.2543 data_time: 0.0100 memory: 13708 grad_norm: 4.3477 loss: 2.4136 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.4136 2023/02/17 23:53:48 - mmengine - INFO - Epoch(train) [8][ 540/1320] lr: 2.0000e-02 eta: 4:03:41 time: 0.2547 data_time: 0.0105 memory: 13708 grad_norm: 4.2523 loss: 2.3345 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.3345 2023/02/17 23:53:53 - mmengine - INFO - Epoch(train) [8][ 560/1320] lr: 2.0000e-02 eta: 4:03:35 time: 0.2540 data_time: 0.0104 memory: 13708 grad_norm: 4.3093 loss: 2.2512 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.2512 2023/02/17 23:53:58 - mmengine - INFO - Epoch(train) [8][ 580/1320] lr: 2.0000e-02 eta: 4:03:30 time: 0.2559 data_time: 0.0112 memory: 13708 grad_norm: 4.1913 loss: 2.5153 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.5153 2023/02/17 23:54:03 - mmengine - INFO - Epoch(train) [8][ 600/1320] lr: 2.0000e-02 eta: 4:03:24 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.4039 loss: 2.1342 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.1342 2023/02/17 23:54:08 - mmengine - INFO - Epoch(train) [8][ 620/1320] lr: 2.0000e-02 eta: 4:03:18 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.4346 loss: 2.4201 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.4201 2023/02/17 23:54:14 - mmengine - INFO - Epoch(train) [8][ 640/1320] lr: 2.0000e-02 eta: 4:03:12 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.1952 loss: 2.0423 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0423 2023/02/17 23:54:19 - mmengine - INFO - Epoch(train) [8][ 660/1320] lr: 2.0000e-02 eta: 4:03:06 time: 0.2545 data_time: 0.0103 memory: 13708 grad_norm: 4.3184 loss: 2.3536 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.3536 2023/02/17 23:54:24 - mmengine - INFO - Epoch(train) [8][ 680/1320] lr: 2.0000e-02 eta: 4:03:00 time: 0.2544 data_time: 0.0103 memory: 13708 grad_norm: 4.3111 loss: 2.2662 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.2662 2023/02/17 23:54:29 - mmengine - INFO - Epoch(train) [8][ 700/1320] lr: 2.0000e-02 eta: 4:02:55 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.2486 loss: 2.0813 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.0813 2023/02/17 23:54:34 - mmengine - INFO - Epoch(train) [8][ 720/1320] lr: 2.0000e-02 eta: 4:02:49 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.2500 loss: 2.3835 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3835 2023/02/17 23:54:39 - mmengine - INFO - Epoch(train) [8][ 740/1320] lr: 2.0000e-02 eta: 4:02:43 time: 0.2559 data_time: 0.0117 memory: 13708 grad_norm: 4.4576 loss: 2.4030 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.4030 2023/02/17 23:54:44 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:54:44 - mmengine - INFO - Epoch(train) [8][ 760/1320] lr: 2.0000e-02 eta: 4:02:38 time: 0.2554 data_time: 0.0100 memory: 13708 grad_norm: 4.3742 loss: 2.1482 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1482 2023/02/17 23:54:49 - mmengine - INFO - Epoch(train) [8][ 780/1320] lr: 2.0000e-02 eta: 4:02:32 time: 0.2541 data_time: 0.0103 memory: 13708 grad_norm: 4.3974 loss: 2.0743 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 2.0743 2023/02/17 23:54:54 - mmengine - INFO - Epoch(train) [8][ 800/1320] lr: 2.0000e-02 eta: 4:02:26 time: 0.2538 data_time: 0.0099 memory: 13708 grad_norm: 4.2186 loss: 2.4871 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.4871 2023/02/17 23:54:59 - mmengine - INFO - Epoch(train) [8][ 820/1320] lr: 2.0000e-02 eta: 4:02:20 time: 0.2541 data_time: 0.0100 memory: 13708 grad_norm: 4.4426 loss: 2.4395 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.4395 2023/02/17 23:55:04 - mmengine - INFO - Epoch(train) [8][ 840/1320] lr: 2.0000e-02 eta: 4:02:14 time: 0.2537 data_time: 0.0100 memory: 13708 grad_norm: 4.2584 loss: 2.2020 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.2020 2023/02/17 23:55:10 - mmengine - INFO - Epoch(train) [8][ 860/1320] lr: 2.0000e-02 eta: 4:02:08 time: 0.2543 data_time: 0.0100 memory: 13708 grad_norm: 4.3006 loss: 2.0709 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.0709 2023/02/17 23:55:15 - mmengine - INFO - Epoch(train) [8][ 880/1320] lr: 2.0000e-02 eta: 4:02:03 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 4.3102 loss: 2.1014 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.1014 2023/02/17 23:55:20 - mmengine - INFO - Epoch(train) [8][ 900/1320] lr: 2.0000e-02 eta: 4:01:57 time: 0.2566 data_time: 0.0111 memory: 13708 grad_norm: 4.2368 loss: 2.2830 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2830 2023/02/17 23:55:25 - mmengine - INFO - Epoch(train) [8][ 920/1320] lr: 2.0000e-02 eta: 4:01:51 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.2417 loss: 2.3992 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.3992 2023/02/17 23:55:30 - mmengine - INFO - Epoch(train) [8][ 940/1320] lr: 2.0000e-02 eta: 4:01:46 time: 0.2563 data_time: 0.0121 memory: 13708 grad_norm: 4.2223 loss: 2.2766 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 2.2766 2023/02/17 23:55:35 - mmengine - INFO - Epoch(train) [8][ 960/1320] lr: 2.0000e-02 eta: 4:01:40 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.3260 loss: 2.2936 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.2936 2023/02/17 23:55:40 - mmengine - INFO - Epoch(train) [8][ 980/1320] lr: 2.0000e-02 eta: 4:01:34 time: 0.2547 data_time: 0.0101 memory: 13708 grad_norm: 4.3126 loss: 2.2758 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.2758 2023/02/17 23:55:45 - mmengine - INFO - Epoch(train) [8][1000/1320] lr: 2.0000e-02 eta: 4:01:28 time: 0.2549 data_time: 0.0104 memory: 13708 grad_norm: 4.1183 loss: 2.2855 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.2855 2023/02/17 23:55:50 - mmengine - INFO - Epoch(train) [8][1020/1320] lr: 2.0000e-02 eta: 4:01:23 time: 0.2561 data_time: 0.0115 memory: 13708 grad_norm: 4.3129 loss: 2.3288 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.3288 2023/02/17 23:55:56 - mmengine - INFO - Epoch(train) [8][1040/1320] lr: 2.0000e-02 eta: 4:01:17 time: 0.2568 data_time: 0.0121 memory: 13708 grad_norm: 4.3735 loss: 2.2875 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.2875 2023/02/17 23:56:01 - mmengine - INFO - Epoch(train) [8][1060/1320] lr: 2.0000e-02 eta: 4:01:12 time: 0.2546 data_time: 0.0101 memory: 13708 grad_norm: 4.2243 loss: 2.0925 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0925 2023/02/17 23:56:06 - mmengine - INFO - Epoch(train) [8][1080/1320] lr: 2.0000e-02 eta: 4:01:06 time: 0.2548 data_time: 0.0104 memory: 13708 grad_norm: 4.2797 loss: 2.1423 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.1423 2023/02/17 23:56:11 - mmengine - INFO - Epoch(train) [8][1100/1320] lr: 2.0000e-02 eta: 4:01:00 time: 0.2559 data_time: 0.0112 memory: 13708 grad_norm: 4.3182 loss: 2.3474 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.3474 2023/02/17 23:56:16 - mmengine - INFO - Epoch(train) [8][1120/1320] lr: 2.0000e-02 eta: 4:00:54 time: 0.2547 data_time: 0.0102 memory: 13708 grad_norm: 4.3780 loss: 2.3396 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.3396 2023/02/17 23:56:21 - mmengine - INFO - Epoch(train) [8][1140/1320] lr: 2.0000e-02 eta: 4:00:49 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.3330 loss: 2.3032 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3032 2023/02/17 23:56:26 - mmengine - INFO - Epoch(train) [8][1160/1320] lr: 2.0000e-02 eta: 4:00:43 time: 0.2541 data_time: 0.0102 memory: 13708 grad_norm: 4.3345 loss: 2.0099 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0099 2023/02/17 23:56:31 - mmengine - INFO - Epoch(train) [8][1180/1320] lr: 2.0000e-02 eta: 4:00:37 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.3451 loss: 2.3076 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.3076 2023/02/17 23:56:36 - mmengine - INFO - Epoch(train) [8][1200/1320] lr: 2.0000e-02 eta: 4:00:31 time: 0.2544 data_time: 0.0102 memory: 13708 grad_norm: 4.4888 loss: 2.2835 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.2835 2023/02/17 23:56:41 - mmengine - INFO - Epoch(train) [8][1220/1320] lr: 2.0000e-02 eta: 4:00:26 time: 0.2554 data_time: 0.0099 memory: 13708 grad_norm: 4.1164 loss: 2.3044 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.3044 2023/02/17 23:56:47 - mmengine - INFO - Epoch(train) [8][1240/1320] lr: 2.0000e-02 eta: 4:00:20 time: 0.2541 data_time: 0.0103 memory: 13708 grad_norm: 4.2908 loss: 2.2552 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 2.2552 2023/02/17 23:56:52 - mmengine - INFO - Epoch(train) [8][1260/1320] lr: 2.0000e-02 eta: 4:00:14 time: 0.2543 data_time: 0.0103 memory: 13708 grad_norm: 4.2549 loss: 2.3642 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.3642 2023/02/17 23:56:57 - mmengine - INFO - Epoch(train) [8][1280/1320] lr: 2.0000e-02 eta: 4:00:08 time: 0.2546 data_time: 0.0099 memory: 13708 grad_norm: 4.2538 loss: 2.4120 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.4120 2023/02/17 23:57:02 - mmengine - INFO - Epoch(train) [8][1300/1320] lr: 2.0000e-02 eta: 4:00:03 time: 0.2543 data_time: 0.0104 memory: 13708 grad_norm: 4.2473 loss: 2.3888 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.3888 2023/02/17 23:57:07 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:57:07 - mmengine - INFO - Epoch(train) [8][1320/1320] lr: 2.0000e-02 eta: 3:59:57 time: 0.2500 data_time: 0.0102 memory: 13708 grad_norm: 4.2315 loss: 2.3025 top1_acc: 0.4545 top5_acc: 0.7273 loss_cls: 2.3025 2023/02/17 23:57:09 - mmengine - INFO - Epoch(val) [8][ 20/194] eta: 0:00:21 time: 0.1253 data_time: 0.0575 memory: 1818 2023/02/17 23:57:11 - mmengine - INFO - Epoch(val) [8][ 40/194] eta: 0:00:16 time: 0.0906 data_time: 0.0227 memory: 1818 2023/02/17 23:57:13 - mmengine - INFO - Epoch(val) [8][ 60/194] eta: 0:00:13 time: 0.0886 data_time: 0.0210 memory: 1818 2023/02/17 23:57:15 - mmengine - INFO - Epoch(val) [8][ 80/194] eta: 0:00:11 time: 0.0889 data_time: 0.0210 memory: 1818 2023/02/17 23:57:17 - mmengine - INFO - Epoch(val) [8][100/194] eta: 0:00:09 time: 0.0930 data_time: 0.0260 memory: 1818 2023/02/17 23:57:18 - mmengine - INFO - Epoch(val) [8][120/194] eta: 0:00:07 time: 0.0862 data_time: 0.0182 memory: 1818 2023/02/17 23:57:20 - mmengine - INFO - Epoch(val) [8][140/194] eta: 0:00:05 time: 0.0906 data_time: 0.0221 memory: 1818 2023/02/17 23:57:22 - mmengine - INFO - Epoch(val) [8][160/194] eta: 0:00:03 time: 0.0788 data_time: 0.0118 memory: 1818 2023/02/17 23:57:23 - mmengine - INFO - Epoch(val) [8][180/194] eta: 0:00:01 time: 0.0852 data_time: 0.0179 memory: 1818 2023/02/17 23:57:25 - mmengine - INFO - Epoch(val) [8][194/194] acc/top1: 0.4082 acc/top5: 0.7123 acc/mean1: 0.3426 2023/02/17 23:57:25 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_7.pth is removed 2023/02/17 23:57:26 - mmengine - INFO - The best checkpoint with 0.4082 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2023/02/17 23:57:32 - mmengine - INFO - Epoch(train) [9][ 20/1320] lr: 2.0000e-02 eta: 3:59:54 time: 0.2887 data_time: 0.0386 memory: 13708 grad_norm: 4.2378 loss: 2.3428 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.3428 2023/02/17 23:57:37 - mmengine - INFO - Epoch(train) [9][ 40/1320] lr: 2.0000e-02 eta: 3:59:49 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 4.2814 loss: 2.2009 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.2009 2023/02/17 23:57:42 - mmengine - INFO - Epoch(train) [9][ 60/1320] lr: 2.0000e-02 eta: 3:59:43 time: 0.2542 data_time: 0.0102 memory: 13708 grad_norm: 4.3245 loss: 2.2065 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.2065 2023/02/17 23:57:47 - mmengine - INFO - Epoch(train) [9][ 80/1320] lr: 2.0000e-02 eta: 3:59:37 time: 0.2540 data_time: 0.0104 memory: 13708 grad_norm: 4.3356 loss: 2.3951 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.3951 2023/02/17 23:57:52 - mmengine - INFO - Epoch(train) [9][ 100/1320] lr: 2.0000e-02 eta: 3:59:31 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.2467 loss: 2.1299 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.1299 2023/02/17 23:57:57 - mmengine - INFO - Epoch(train) [9][ 120/1320] lr: 2.0000e-02 eta: 3:59:26 time: 0.2538 data_time: 0.0105 memory: 13708 grad_norm: 4.2380 loss: 2.1510 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1510 2023/02/17 23:58:03 - mmengine - INFO - Epoch(train) [9][ 140/1320] lr: 2.0000e-02 eta: 3:59:20 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 4.4542 loss: 2.3705 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.3705 2023/02/17 23:58:08 - mmengine - INFO - Epoch(train) [9][ 160/1320] lr: 2.0000e-02 eta: 3:59:14 time: 0.2544 data_time: 0.0101 memory: 13708 grad_norm: 4.3798 loss: 2.0719 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.0719 2023/02/17 23:58:13 - mmengine - INFO - Epoch(train) [9][ 180/1320] lr: 2.0000e-02 eta: 3:59:08 time: 0.2541 data_time: 0.0103 memory: 13708 grad_norm: 4.4425 loss: 2.1331 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1331 2023/02/17 23:58:18 - mmengine - INFO - Epoch(train) [9][ 200/1320] lr: 2.0000e-02 eta: 3:59:03 time: 0.2552 data_time: 0.0103 memory: 13708 grad_norm: 4.3579 loss: 2.2209 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.2209 2023/02/17 23:58:23 - mmengine - INFO - Epoch(train) [9][ 220/1320] lr: 2.0000e-02 eta: 3:58:57 time: 0.2539 data_time: 0.0100 memory: 13708 grad_norm: 4.2345 loss: 2.2537 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.2537 2023/02/17 23:58:28 - mmengine - INFO - Epoch(train) [9][ 240/1320] lr: 2.0000e-02 eta: 3:58:51 time: 0.2544 data_time: 0.0101 memory: 13708 grad_norm: 4.4311 loss: 2.1912 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.1912 2023/02/17 23:58:33 - mmengine - INFO - Epoch(train) [9][ 260/1320] lr: 2.0000e-02 eta: 3:58:45 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.2846 loss: 2.2324 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.2324 2023/02/17 23:58:38 - mmengine - INFO - Epoch(train) [9][ 280/1320] lr: 2.0000e-02 eta: 3:58:40 time: 0.2541 data_time: 0.0102 memory: 13708 grad_norm: 4.3235 loss: 2.2918 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.2918 2023/02/17 23:58:43 - mmengine - INFO - Epoch(train) [9][ 300/1320] lr: 2.0000e-02 eta: 3:58:34 time: 0.2567 data_time: 0.0122 memory: 13708 grad_norm: 4.3226 loss: 2.3484 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.3484 2023/02/17 23:58:48 - mmengine - INFO - Epoch(train) [9][ 320/1320] lr: 2.0000e-02 eta: 3:58:29 time: 0.2555 data_time: 0.0117 memory: 13708 grad_norm: 4.3496 loss: 2.2501 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.2501 2023/02/17 23:58:53 - mmengine - INFO - Epoch(train) [9][ 340/1320] lr: 2.0000e-02 eta: 3:58:23 time: 0.2548 data_time: 0.0111 memory: 13708 grad_norm: 4.2914 loss: 2.1996 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.1996 2023/02/17 23:58:59 - mmengine - INFO - Epoch(train) [9][ 360/1320] lr: 2.0000e-02 eta: 3:58:17 time: 0.2556 data_time: 0.0102 memory: 13708 grad_norm: 4.3261 loss: 2.2575 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.2575 2023/02/17 23:59:04 - mmengine - INFO - Epoch(train) [9][ 380/1320] lr: 2.0000e-02 eta: 3:58:12 time: 0.2544 data_time: 0.0102 memory: 13708 grad_norm: 4.3452 loss: 2.2176 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.2176 2023/02/17 23:59:09 - mmengine - INFO - Epoch(train) [9][ 400/1320] lr: 2.0000e-02 eta: 3:58:06 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 4.2765 loss: 2.2793 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.2793 2023/02/17 23:59:14 - mmengine - INFO - Epoch(train) [9][ 420/1320] lr: 2.0000e-02 eta: 3:58:01 time: 0.2565 data_time: 0.0125 memory: 13708 grad_norm: 4.4258 loss: 2.1126 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1126 2023/02/17 23:59:19 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/17 23:59:19 - mmengine - INFO - Epoch(train) [9][ 440/1320] lr: 2.0000e-02 eta: 3:57:55 time: 0.2561 data_time: 0.0120 memory: 13708 grad_norm: 4.3541 loss: 2.0916 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 2.0916 2023/02/17 23:59:24 - mmengine - INFO - Epoch(train) [9][ 460/1320] lr: 2.0000e-02 eta: 3:57:49 time: 0.2549 data_time: 0.0098 memory: 13708 grad_norm: 4.2677 loss: 2.0715 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0715 2023/02/17 23:59:29 - mmengine - INFO - Epoch(train) [9][ 480/1320] lr: 2.0000e-02 eta: 3:57:44 time: 0.2551 data_time: 0.0101 memory: 13708 grad_norm: 4.3425 loss: 2.1188 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1188 2023/02/17 23:59:34 - mmengine - INFO - Epoch(train) [9][ 500/1320] lr: 2.0000e-02 eta: 3:57:38 time: 0.2542 data_time: 0.0104 memory: 13708 grad_norm: 4.2474 loss: 2.3360 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.3360 2023/02/17 23:59:39 - mmengine - INFO - Epoch(train) [9][ 520/1320] lr: 2.0000e-02 eta: 3:57:32 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.4432 loss: 2.3013 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.3013 2023/02/17 23:59:45 - mmengine - INFO - Epoch(train) [9][ 540/1320] lr: 2.0000e-02 eta: 3:57:27 time: 0.2548 data_time: 0.0102 memory: 13708 grad_norm: 4.3009 loss: 2.1797 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1797 2023/02/17 23:59:50 - mmengine - INFO - Epoch(train) [9][ 560/1320] lr: 2.0000e-02 eta: 3:57:21 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.3225 loss: 2.4014 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.4014 2023/02/17 23:59:55 - mmengine - INFO - Epoch(train) [9][ 580/1320] lr: 2.0000e-02 eta: 3:57:15 time: 0.2546 data_time: 0.0100 memory: 13708 grad_norm: 4.3907 loss: 2.2668 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.2668 2023/02/18 00:00:00 - mmengine - INFO - Epoch(train) [9][ 600/1320] lr: 2.0000e-02 eta: 3:57:10 time: 0.2541 data_time: 0.0101 memory: 13708 grad_norm: 4.4095 loss: 2.1537 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.1537 2023/02/18 00:00:05 - mmengine - INFO - Epoch(train) [9][ 620/1320] lr: 2.0000e-02 eta: 3:57:04 time: 0.2546 data_time: 0.0108 memory: 13708 grad_norm: 4.3232 loss: 2.2208 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.2208 2023/02/18 00:00:10 - mmengine - INFO - Epoch(train) [9][ 640/1320] lr: 2.0000e-02 eta: 3:56:58 time: 0.2560 data_time: 0.0116 memory: 13708 grad_norm: 4.1829 loss: 2.2637 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.2637 2023/02/18 00:00:15 - mmengine - INFO - Epoch(train) [9][ 660/1320] lr: 2.0000e-02 eta: 3:56:53 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.2854 loss: 2.3176 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.3176 2023/02/18 00:00:21 - mmengine - INFO - Epoch(train) [9][ 680/1320] lr: 2.0000e-02 eta: 3:56:50 time: 0.2855 data_time: 0.0409 memory: 13708 grad_norm: 4.3647 loss: 2.3251 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.3251 2023/02/18 00:00:26 - mmengine - INFO - Epoch(train) [9][ 700/1320] lr: 2.0000e-02 eta: 3:56:45 time: 0.2542 data_time: 0.0099 memory: 13708 grad_norm: 4.3186 loss: 2.1490 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.1490 2023/02/18 00:00:31 - mmengine - INFO - Epoch(train) [9][ 720/1320] lr: 2.0000e-02 eta: 3:56:39 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 4.4226 loss: 2.3478 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.3478 2023/02/18 00:00:36 - mmengine - INFO - Epoch(train) [9][ 740/1320] lr: 2.0000e-02 eta: 3:56:33 time: 0.2544 data_time: 0.0104 memory: 13708 grad_norm: 4.2653 loss: 2.3427 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.3427 2023/02/18 00:00:41 - mmengine - INFO - Epoch(train) [9][ 760/1320] lr: 2.0000e-02 eta: 3:56:28 time: 0.2541 data_time: 0.0099 memory: 13708 grad_norm: 4.3512 loss: 2.1897 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.1897 2023/02/18 00:00:46 - mmengine - INFO - Epoch(train) [9][ 780/1320] lr: 2.0000e-02 eta: 3:56:22 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.3958 loss: 2.2601 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.2601 2023/02/18 00:00:51 - mmengine - INFO - Epoch(train) [9][ 800/1320] lr: 2.0000e-02 eta: 3:56:16 time: 0.2545 data_time: 0.0104 memory: 13708 grad_norm: 4.2264 loss: 2.3068 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.3068 2023/02/18 00:00:56 - mmengine - INFO - Epoch(train) [9][ 820/1320] lr: 2.0000e-02 eta: 3:56:11 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.3009 loss: 2.2738 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.2738 2023/02/18 00:01:02 - mmengine - INFO - Epoch(train) [9][ 840/1320] lr: 2.0000e-02 eta: 3:56:05 time: 0.2551 data_time: 0.0102 memory: 13708 grad_norm: 4.2271 loss: 2.0783 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0783 2023/02/18 00:01:07 - mmengine - INFO - Epoch(train) [9][ 860/1320] lr: 2.0000e-02 eta: 3:55:59 time: 0.2545 data_time: 0.0103 memory: 13708 grad_norm: 4.3708 loss: 2.4472 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.4472 2023/02/18 00:01:13 - mmengine - INFO - Epoch(train) [9][ 880/1320] lr: 2.0000e-02 eta: 3:55:58 time: 0.2947 data_time: 0.0507 memory: 13708 grad_norm: 4.2244 loss: 2.3208 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.3208 2023/02/18 00:01:18 - mmengine - INFO - Epoch(train) [9][ 900/1320] lr: 2.0000e-02 eta: 3:55:52 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.2327 loss: 2.2528 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.2528 2023/02/18 00:01:23 - mmengine - INFO - Epoch(train) [9][ 920/1320] lr: 2.0000e-02 eta: 3:55:46 time: 0.2544 data_time: 0.0104 memory: 13708 grad_norm: 4.2381 loss: 2.2344 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.2344 2023/02/18 00:01:28 - mmengine - INFO - Epoch(train) [9][ 940/1320] lr: 2.0000e-02 eta: 3:55:41 time: 0.2545 data_time: 0.0107 memory: 13708 grad_norm: 4.3110 loss: 2.3030 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.3030 2023/02/18 00:01:33 - mmengine - INFO - Epoch(train) [9][ 960/1320] lr: 2.0000e-02 eta: 3:55:35 time: 0.2545 data_time: 0.0106 memory: 13708 grad_norm: 4.3326 loss: 2.2647 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.2647 2023/02/18 00:01:38 - mmengine - INFO - Epoch(train) [9][ 980/1320] lr: 2.0000e-02 eta: 3:55:29 time: 0.2551 data_time: 0.0113 memory: 13708 grad_norm: 4.4633 loss: 2.1985 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.1985 2023/02/18 00:01:43 - mmengine - INFO - Epoch(train) [9][1000/1320] lr: 2.0000e-02 eta: 3:55:24 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.1693 loss: 2.1874 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.1874 2023/02/18 00:01:48 - mmengine - INFO - Epoch(train) [9][1020/1320] lr: 2.0000e-02 eta: 3:55:18 time: 0.2566 data_time: 0.0114 memory: 13708 grad_norm: 4.3091 loss: 2.2601 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.2601 2023/02/18 00:01:53 - mmengine - INFO - Epoch(train) [9][1040/1320] lr: 2.0000e-02 eta: 3:55:13 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 4.3028 loss: 2.3253 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.3253 2023/02/18 00:01:58 - mmengine - INFO - Epoch(train) [9][1060/1320] lr: 2.0000e-02 eta: 3:55:07 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.3365 loss: 1.9462 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9462 2023/02/18 00:02:04 - mmengine - INFO - Epoch(train) [9][1080/1320] lr: 2.0000e-02 eta: 3:55:02 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 4.3514 loss: 2.3438 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.3438 2023/02/18 00:02:09 - mmengine - INFO - Epoch(train) [9][1100/1320] lr: 2.0000e-02 eta: 3:54:56 time: 0.2555 data_time: 0.0111 memory: 13708 grad_norm: 4.2315 loss: 2.3074 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.3074 2023/02/18 00:02:14 - mmengine - INFO - Epoch(train) [9][1120/1320] lr: 2.0000e-02 eta: 3:54:50 time: 0.2546 data_time: 0.0105 memory: 13708 grad_norm: 4.4078 loss: 2.3115 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.3115 2023/02/18 00:02:19 - mmengine - INFO - Epoch(train) [9][1140/1320] lr: 2.0000e-02 eta: 3:54:45 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 4.4434 loss: 2.1266 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.1266 2023/02/18 00:02:24 - mmengine - INFO - Epoch(train) [9][1160/1320] lr: 2.0000e-02 eta: 3:54:39 time: 0.2551 data_time: 0.0102 memory: 13708 grad_norm: 4.2246 loss: 2.3279 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.3279 2023/02/18 00:02:29 - mmengine - INFO - Epoch(train) [9][1180/1320] lr: 2.0000e-02 eta: 3:54:33 time: 0.2543 data_time: 0.0107 memory: 13708 grad_norm: 4.3541 loss: 2.1315 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1315 2023/02/18 00:02:34 - mmengine - INFO - Epoch(train) [9][1200/1320] lr: 2.0000e-02 eta: 3:54:28 time: 0.2548 data_time: 0.0103 memory: 13708 grad_norm: 4.4593 loss: 2.1604 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 2.1604 2023/02/18 00:02:39 - mmengine - INFO - Epoch(train) [9][1220/1320] lr: 2.0000e-02 eta: 3:54:22 time: 0.2546 data_time: 0.0100 memory: 13708 grad_norm: 4.3854 loss: 2.2762 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.2762 2023/02/18 00:02:44 - mmengine - INFO - Epoch(train) [9][1240/1320] lr: 2.0000e-02 eta: 3:54:17 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.2765 loss: 2.3021 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.3021 2023/02/18 00:02:49 - mmengine - INFO - Epoch(train) [9][1260/1320] lr: 2.0000e-02 eta: 3:54:11 time: 0.2542 data_time: 0.0103 memory: 13708 grad_norm: 4.2621 loss: 2.4388 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.4388 2023/02/18 00:02:55 - mmengine - INFO - Epoch(train) [9][1280/1320] lr: 2.0000e-02 eta: 3:54:05 time: 0.2546 data_time: 0.0105 memory: 13708 grad_norm: 4.2635 loss: 2.1159 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.1159 2023/02/18 00:03:00 - mmengine - INFO - Epoch(train) [9][1300/1320] lr: 2.0000e-02 eta: 3:54:00 time: 0.2549 data_time: 0.0110 memory: 13708 grad_norm: 4.3672 loss: 2.2813 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2813 2023/02/18 00:03:05 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:03:05 - mmengine - INFO - Epoch(train) [9][1320/1320] lr: 2.0000e-02 eta: 3:53:54 time: 0.2505 data_time: 0.0103 memory: 13708 grad_norm: 4.4375 loss: 2.3501 top1_acc: 0.4545 top5_acc: 0.6364 loss_cls: 2.3501 2023/02/18 00:03:05 - mmengine - INFO - Saving checkpoint at 9 epochs 2023/02/18 00:03:08 - mmengine - INFO - Epoch(val) [9][ 20/194] eta: 0:00:22 time: 0.1311 data_time: 0.0623 memory: 1818 2023/02/18 00:03:10 - mmengine - INFO - Epoch(val) [9][ 40/194] eta: 0:00:16 time: 0.0865 data_time: 0.0124 memory: 1818 2023/02/18 00:03:12 - mmengine - INFO - Epoch(val) [9][ 60/194] eta: 0:00:13 time: 0.0877 data_time: 0.0192 memory: 1818 2023/02/18 00:03:14 - mmengine - INFO - Epoch(val) [9][ 80/194] eta: 0:00:11 time: 0.0857 data_time: 0.0173 memory: 1818 2023/02/18 00:03:16 - mmengine - INFO - Epoch(val) [9][100/194] eta: 0:00:09 time: 0.0969 data_time: 0.0278 memory: 1818 2023/02/18 00:03:17 - mmengine - INFO - Epoch(val) [9][120/194] eta: 0:00:07 time: 0.0833 data_time: 0.0146 memory: 1818 2023/02/18 00:03:19 - mmengine - INFO - Epoch(val) [9][140/194] eta: 0:00:05 time: 0.0950 data_time: 0.0267 memory: 1818 2023/02/18 00:03:21 - mmengine - INFO - Epoch(val) [9][160/194] eta: 0:00:03 time: 0.0801 data_time: 0.0118 memory: 1818 2023/02/18 00:03:22 - mmengine - INFO - Epoch(val) [9][180/194] eta: 0:00:01 time: 0.0797 data_time: 0.0141 memory: 1818 2023/02/18 00:03:24 - mmengine - INFO - Epoch(val) [9][194/194] acc/top1: 0.4023 acc/top5: 0.6991 acc/mean1: 0.3395 2023/02/18 00:03:30 - mmengine - INFO - Epoch(train) [10][ 20/1320] lr: 2.0000e-02 eta: 3:53:53 time: 0.3035 data_time: 0.0500 memory: 13708 grad_norm: 4.2127 loss: 1.8870 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 1.8870 2023/02/18 00:03:35 - mmengine - INFO - Epoch(train) [10][ 40/1320] lr: 2.0000e-02 eta: 3:53:47 time: 0.2564 data_time: 0.0113 memory: 13708 grad_norm: 4.2533 loss: 2.2236 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2236 2023/02/18 00:03:40 - mmengine - INFO - Epoch(train) [10][ 60/1320] lr: 2.0000e-02 eta: 3:53:42 time: 0.2544 data_time: 0.0105 memory: 13708 grad_norm: 4.4712 loss: 2.4936 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.4936 2023/02/18 00:03:45 - mmengine - INFO - Epoch(train) [10][ 80/1320] lr: 2.0000e-02 eta: 3:53:36 time: 0.2545 data_time: 0.0109 memory: 13708 grad_norm: 4.3302 loss: 2.0780 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0780 2023/02/18 00:03:51 - mmengine - INFO - Epoch(train) [10][ 100/1320] lr: 2.0000e-02 eta: 3:53:30 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 4.3392 loss: 2.1387 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1387 2023/02/18 00:03:56 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:03:56 - mmengine - INFO - Epoch(train) [10][ 120/1320] lr: 2.0000e-02 eta: 3:53:25 time: 0.2551 data_time: 0.0111 memory: 13708 grad_norm: 4.2405 loss: 2.2962 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.2962 2023/02/18 00:04:01 - mmengine - INFO - Epoch(train) [10][ 140/1320] lr: 2.0000e-02 eta: 3:53:19 time: 0.2550 data_time: 0.0113 memory: 13708 grad_norm: 4.3715 loss: 2.3001 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.3001 2023/02/18 00:04:06 - mmengine - INFO - Epoch(train) [10][ 160/1320] lr: 2.0000e-02 eta: 3:53:14 time: 0.2562 data_time: 0.0117 memory: 13708 grad_norm: 4.3448 loss: 2.2993 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.2993 2023/02/18 00:04:11 - mmengine - INFO - Epoch(train) [10][ 180/1320] lr: 2.0000e-02 eta: 3:53:08 time: 0.2546 data_time: 0.0109 memory: 13708 grad_norm: 4.2978 loss: 2.2262 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.2262 2023/02/18 00:04:16 - mmengine - INFO - Epoch(train) [10][ 200/1320] lr: 2.0000e-02 eta: 3:53:03 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.3646 loss: 2.3281 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.3281 2023/02/18 00:04:21 - mmengine - INFO - Epoch(train) [10][ 220/1320] lr: 2.0000e-02 eta: 3:52:57 time: 0.2556 data_time: 0.0114 memory: 13708 grad_norm: 4.3504 loss: 2.2689 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.2689 2023/02/18 00:04:26 - mmengine - INFO - Epoch(train) [10][ 240/1320] lr: 2.0000e-02 eta: 3:52:52 time: 0.2552 data_time: 0.0113 memory: 13708 grad_norm: 4.3119 loss: 2.2938 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.2938 2023/02/18 00:04:31 - mmengine - INFO - Epoch(train) [10][ 260/1320] lr: 2.0000e-02 eta: 3:52:46 time: 0.2549 data_time: 0.0111 memory: 13708 grad_norm: 4.4354 loss: 2.3317 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.3317 2023/02/18 00:04:37 - mmengine - INFO - Epoch(train) [10][ 280/1320] lr: 2.0000e-02 eta: 3:52:41 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 4.4113 loss: 2.1391 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.1391 2023/02/18 00:04:42 - mmengine - INFO - Epoch(train) [10][ 300/1320] lr: 2.0000e-02 eta: 3:52:35 time: 0.2550 data_time: 0.0112 memory: 13708 grad_norm: 4.3465 loss: 2.3974 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.3974 2023/02/18 00:04:47 - mmengine - INFO - Epoch(train) [10][ 320/1320] lr: 2.0000e-02 eta: 3:52:29 time: 0.2557 data_time: 0.0115 memory: 13708 grad_norm: 4.4525 loss: 1.9858 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9858 2023/02/18 00:04:52 - mmengine - INFO - Epoch(train) [10][ 340/1320] lr: 2.0000e-02 eta: 3:52:24 time: 0.2552 data_time: 0.0111 memory: 13708 grad_norm: 4.2850 loss: 2.2120 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.2120 2023/02/18 00:04:57 - mmengine - INFO - Epoch(train) [10][ 360/1320] lr: 2.0000e-02 eta: 3:52:18 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 4.3834 loss: 2.0838 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 2.0838 2023/02/18 00:05:02 - mmengine - INFO - Epoch(train) [10][ 380/1320] lr: 2.0000e-02 eta: 3:52:13 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 4.4109 loss: 2.3424 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3424 2023/02/18 00:05:07 - mmengine - INFO - Epoch(train) [10][ 400/1320] lr: 2.0000e-02 eta: 3:52:07 time: 0.2549 data_time: 0.0110 memory: 13708 grad_norm: 4.3120 loss: 1.9897 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9897 2023/02/18 00:05:12 - mmengine - INFO - Epoch(train) [10][ 420/1320] lr: 2.0000e-02 eta: 3:52:02 time: 0.2556 data_time: 0.0111 memory: 13708 grad_norm: 4.2050 loss: 2.1898 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.1898 2023/02/18 00:05:17 - mmengine - INFO - Epoch(train) [10][ 440/1320] lr: 2.0000e-02 eta: 3:51:56 time: 0.2566 data_time: 0.0111 memory: 13708 grad_norm: 4.3795 loss: 2.2297 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.2297 2023/02/18 00:05:23 - mmengine - INFO - Epoch(train) [10][ 460/1320] lr: 2.0000e-02 eta: 3:51:51 time: 0.2558 data_time: 0.0112 memory: 13708 grad_norm: 4.1916 loss: 2.3628 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.3628 2023/02/18 00:05:28 - mmengine - INFO - Epoch(train) [10][ 480/1320] lr: 2.0000e-02 eta: 3:51:45 time: 0.2562 data_time: 0.0119 memory: 13708 grad_norm: 4.2876 loss: 2.1507 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1507 2023/02/18 00:05:33 - mmengine - INFO - Epoch(train) [10][ 500/1320] lr: 2.0000e-02 eta: 3:51:40 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.3656 loss: 2.0828 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0828 2023/02/18 00:05:38 - mmengine - INFO - Epoch(train) [10][ 520/1320] lr: 2.0000e-02 eta: 3:51:34 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 4.3962 loss: 2.1626 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.1626 2023/02/18 00:05:43 - mmengine - INFO - Epoch(train) [10][ 540/1320] lr: 2.0000e-02 eta: 3:51:29 time: 0.2558 data_time: 0.0111 memory: 13708 grad_norm: 4.5310 loss: 2.3054 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.3054 2023/02/18 00:05:48 - mmengine - INFO - Epoch(train) [10][ 560/1320] lr: 2.0000e-02 eta: 3:51:23 time: 0.2554 data_time: 0.0111 memory: 13708 grad_norm: 4.2717 loss: 2.2245 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.2245 2023/02/18 00:05:53 - mmengine - INFO - Epoch(train) [10][ 580/1320] lr: 2.0000e-02 eta: 3:51:18 time: 0.2566 data_time: 0.0116 memory: 13708 grad_norm: 4.2682 loss: 2.3058 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.3058 2023/02/18 00:05:58 - mmengine - INFO - Epoch(train) [10][ 600/1320] lr: 2.0000e-02 eta: 3:51:13 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 4.3753 loss: 2.4108 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.4108 2023/02/18 00:06:03 - mmengine - INFO - Epoch(train) [10][ 620/1320] lr: 2.0000e-02 eta: 3:51:07 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.3848 loss: 2.1984 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.1984 2023/02/18 00:06:09 - mmengine - INFO - Epoch(train) [10][ 640/1320] lr: 2.0000e-02 eta: 3:51:02 time: 0.2546 data_time: 0.0102 memory: 13708 grad_norm: 4.3015 loss: 2.2220 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 2.2220 2023/02/18 00:06:14 - mmengine - INFO - Epoch(train) [10][ 660/1320] lr: 2.0000e-02 eta: 3:50:56 time: 0.2547 data_time: 0.0103 memory: 13708 grad_norm: 4.3365 loss: 2.0484 top1_acc: 0.6250 top5_acc: 0.6250 loss_cls: 2.0484 2023/02/18 00:06:19 - mmengine - INFO - Epoch(train) [10][ 680/1320] lr: 2.0000e-02 eta: 3:50:50 time: 0.2542 data_time: 0.0102 memory: 13708 grad_norm: 4.3380 loss: 2.3156 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 2.3156 2023/02/18 00:06:24 - mmengine - INFO - Epoch(train) [10][ 700/1320] lr: 2.0000e-02 eta: 3:50:45 time: 0.2554 data_time: 0.0113 memory: 13708 grad_norm: 4.4109 loss: 2.1938 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1938 2023/02/18 00:06:29 - mmengine - INFO - Epoch(train) [10][ 720/1320] lr: 2.0000e-02 eta: 3:50:39 time: 0.2556 data_time: 0.0114 memory: 13708 grad_norm: 4.2990 loss: 2.3221 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.3221 2023/02/18 00:06:34 - mmengine - INFO - Epoch(train) [10][ 740/1320] lr: 2.0000e-02 eta: 3:50:34 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.2616 loss: 2.0482 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.0482 2023/02/18 00:06:39 - mmengine - INFO - Epoch(train) [10][ 760/1320] lr: 2.0000e-02 eta: 3:50:28 time: 0.2542 data_time: 0.0101 memory: 13708 grad_norm: 4.3418 loss: 2.1860 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.1860 2023/02/18 00:06:44 - mmengine - INFO - Epoch(train) [10][ 780/1320] lr: 2.0000e-02 eta: 3:50:23 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.2882 loss: 2.1884 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.1884 2023/02/18 00:06:49 - mmengine - INFO - Epoch(train) [10][ 800/1320] lr: 2.0000e-02 eta: 3:50:17 time: 0.2542 data_time: 0.0102 memory: 13708 grad_norm: 4.3344 loss: 2.4449 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.4449 2023/02/18 00:06:54 - mmengine - INFO - Epoch(train) [10][ 820/1320] lr: 2.0000e-02 eta: 3:50:11 time: 0.2541 data_time: 0.0103 memory: 13708 grad_norm: 4.2426 loss: 2.2961 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.2961 2023/02/18 00:07:00 - mmengine - INFO - Epoch(train) [10][ 840/1320] lr: 2.0000e-02 eta: 3:50:06 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 4.3032 loss: 1.9954 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9954 2023/02/18 00:07:05 - mmengine - INFO - Epoch(train) [10][ 860/1320] lr: 2.0000e-02 eta: 3:50:00 time: 0.2545 data_time: 0.0104 memory: 13708 grad_norm: 4.2830 loss: 2.1704 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.1704 2023/02/18 00:07:10 - mmengine - INFO - Epoch(train) [10][ 880/1320] lr: 2.0000e-02 eta: 3:49:55 time: 0.2553 data_time: 0.0115 memory: 13708 grad_norm: 4.3210 loss: 2.1958 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1958 2023/02/18 00:07:15 - mmengine - INFO - Epoch(train) [10][ 900/1320] lr: 2.0000e-02 eta: 3:49:49 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.3212 loss: 2.1186 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.1186 2023/02/18 00:07:20 - mmengine - INFO - Epoch(train) [10][ 920/1320] lr: 2.0000e-02 eta: 3:49:44 time: 0.2550 data_time: 0.0102 memory: 13708 grad_norm: 4.4291 loss: 2.2540 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.2540 2023/02/18 00:07:25 - mmengine - INFO - Epoch(train) [10][ 940/1320] lr: 2.0000e-02 eta: 3:49:38 time: 0.2551 data_time: 0.0107 memory: 13708 grad_norm: 4.2355 loss: 2.1426 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1426 2023/02/18 00:07:30 - mmengine - INFO - Epoch(train) [10][ 960/1320] lr: 2.0000e-02 eta: 3:49:33 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.3345 loss: 2.2342 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.2342 2023/02/18 00:07:35 - mmengine - INFO - Epoch(train) [10][ 980/1320] lr: 2.0000e-02 eta: 3:49:27 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.2257 loss: 2.2729 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.2729 2023/02/18 00:07:40 - mmengine - INFO - Epoch(train) [10][1000/1320] lr: 2.0000e-02 eta: 3:49:22 time: 0.2546 data_time: 0.0107 memory: 13708 grad_norm: 4.2615 loss: 2.0729 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0729 2023/02/18 00:07:45 - mmengine - INFO - Epoch(train) [10][1020/1320] lr: 2.0000e-02 eta: 3:49:16 time: 0.2558 data_time: 0.0114 memory: 13708 grad_norm: 4.2016 loss: 2.1249 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1249 2023/02/18 00:07:51 - mmengine - INFO - Epoch(train) [10][1040/1320] lr: 2.0000e-02 eta: 3:49:11 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.3885 loss: 2.3512 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.3512 2023/02/18 00:07:56 - mmengine - INFO - Epoch(train) [10][1060/1320] lr: 2.0000e-02 eta: 3:49:05 time: 0.2561 data_time: 0.0112 memory: 13708 grad_norm: 4.3670 loss: 2.1756 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.1756 2023/02/18 00:08:01 - mmengine - INFO - Epoch(train) [10][1080/1320] lr: 2.0000e-02 eta: 3:49:00 time: 0.2546 data_time: 0.0103 memory: 13708 grad_norm: 4.3504 loss: 2.2308 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.2308 2023/02/18 00:08:06 - mmengine - INFO - Epoch(train) [10][1100/1320] lr: 2.0000e-02 eta: 3:48:54 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 4.4557 loss: 2.0373 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0373 2023/02/18 00:08:11 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:08:11 - mmengine - INFO - Epoch(train) [10][1120/1320] lr: 2.0000e-02 eta: 3:48:49 time: 0.2544 data_time: 0.0105 memory: 13708 grad_norm: 4.3741 loss: 2.2377 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.2377 2023/02/18 00:08:16 - mmengine - INFO - Epoch(train) [10][1140/1320] lr: 2.0000e-02 eta: 3:48:43 time: 0.2545 data_time: 0.0102 memory: 13708 grad_norm: 4.3252 loss: 2.2427 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.2427 2023/02/18 00:08:21 - mmengine - INFO - Epoch(train) [10][1160/1320] lr: 2.0000e-02 eta: 3:48:38 time: 0.2554 data_time: 0.0103 memory: 13708 grad_norm: 4.2365 loss: 2.2924 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.2924 2023/02/18 00:08:26 - mmengine - INFO - Epoch(train) [10][1180/1320] lr: 2.0000e-02 eta: 3:48:32 time: 0.2550 data_time: 0.0110 memory: 13708 grad_norm: 4.3671 loss: 2.1312 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1312 2023/02/18 00:08:31 - mmengine - INFO - Epoch(train) [10][1200/1320] lr: 2.0000e-02 eta: 3:48:27 time: 0.2546 data_time: 0.0104 memory: 13708 grad_norm: 4.4032 loss: 2.0488 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0488 2023/02/18 00:08:36 - mmengine - INFO - Epoch(train) [10][1220/1320] lr: 2.0000e-02 eta: 3:48:21 time: 0.2545 data_time: 0.0108 memory: 13708 grad_norm: 4.3519 loss: 2.1583 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1583 2023/02/18 00:08:42 - mmengine - INFO - Epoch(train) [10][1240/1320] lr: 2.0000e-02 eta: 3:48:16 time: 0.2553 data_time: 0.0104 memory: 13708 grad_norm: 4.3145 loss: 2.1494 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.1494 2023/02/18 00:08:47 - mmengine - INFO - Epoch(train) [10][1260/1320] lr: 2.0000e-02 eta: 3:48:10 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 4.3480 loss: 2.2049 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.2049 2023/02/18 00:08:52 - mmengine - INFO - Epoch(train) [10][1280/1320] lr: 2.0000e-02 eta: 3:48:05 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.3091 loss: 1.9792 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 1.9792 2023/02/18 00:08:57 - mmengine - INFO - Epoch(train) [10][1300/1320] lr: 2.0000e-02 eta: 3:47:59 time: 0.2552 data_time: 0.0102 memory: 13708 grad_norm: 4.3400 loss: 2.0695 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0695 2023/02/18 00:09:02 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:09:02 - mmengine - INFO - Epoch(train) [10][1320/1320] lr: 2.0000e-02 eta: 3:47:53 time: 0.2503 data_time: 0.0106 memory: 13708 grad_norm: 4.4069 loss: 1.9851 top1_acc: 0.4545 top5_acc: 0.8182 loss_cls: 1.9851 2023/02/18 00:09:04 - mmengine - INFO - Epoch(val) [10][ 20/194] eta: 0:00:21 time: 0.1235 data_time: 0.0556 memory: 1818 2023/02/18 00:09:06 - mmengine - INFO - Epoch(val) [10][ 40/194] eta: 0:00:16 time: 0.0879 data_time: 0.0196 memory: 1818 2023/02/18 00:09:08 - mmengine - INFO - Epoch(val) [10][ 60/194] eta: 0:00:13 time: 0.0880 data_time: 0.0200 memory: 1818 2023/02/18 00:09:10 - mmengine - INFO - Epoch(val) [10][ 80/194] eta: 0:00:10 time: 0.0827 data_time: 0.0150 memory: 1818 2023/02/18 00:09:11 - mmengine - INFO - Epoch(val) [10][100/194] eta: 0:00:08 time: 0.0903 data_time: 0.0224 memory: 1818 2023/02/18 00:09:13 - mmengine - INFO - Epoch(val) [10][120/194] eta: 0:00:06 time: 0.0838 data_time: 0.0157 memory: 1818 2023/02/18 00:09:15 - mmengine - INFO - Epoch(val) [10][140/194] eta: 0:00:04 time: 0.0877 data_time: 0.0202 memory: 1818 2023/02/18 00:09:16 - mmengine - INFO - Epoch(val) [10][160/194] eta: 0:00:03 time: 0.0824 data_time: 0.0151 memory: 1818 2023/02/18 00:09:18 - mmengine - INFO - Epoch(val) [10][180/194] eta: 0:00:01 time: 0.0920 data_time: 0.0241 memory: 1818 2023/02/18 00:09:20 - mmengine - INFO - Epoch(val) [10][194/194] acc/top1: 0.4310 acc/top5: 0.7338 acc/mean1: 0.3508 2023/02/18 00:09:20 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_8.pth is removed 2023/02/18 00:09:21 - mmengine - INFO - The best checkpoint with 0.4310 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2023/02/18 00:09:27 - mmengine - INFO - Epoch(train) [11][ 20/1320] lr: 2.0000e-02 eta: 3:47:51 time: 0.2927 data_time: 0.0401 memory: 13708 grad_norm: 4.3867 loss: 2.2101 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.2101 2023/02/18 00:09:32 - mmengine - INFO - Epoch(train) [11][ 40/1320] lr: 2.0000e-02 eta: 3:47:45 time: 0.2552 data_time: 0.0103 memory: 13708 grad_norm: 4.3597 loss: 2.2968 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.2968 2023/02/18 00:09:37 - mmengine - INFO - Epoch(train) [11][ 60/1320] lr: 2.0000e-02 eta: 3:47:40 time: 0.2540 data_time: 0.0102 memory: 13708 grad_norm: 4.3541 loss: 2.2984 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.2984 2023/02/18 00:09:42 - mmengine - INFO - Epoch(train) [11][ 80/1320] lr: 2.0000e-02 eta: 3:47:34 time: 0.2541 data_time: 0.0099 memory: 13708 grad_norm: 4.4225 loss: 2.1974 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 2.1974 2023/02/18 00:09:47 - mmengine - INFO - Epoch(train) [11][ 100/1320] lr: 2.0000e-02 eta: 3:47:29 time: 0.2545 data_time: 0.0102 memory: 13708 grad_norm: 4.3019 loss: 2.0868 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0868 2023/02/18 00:09:53 - mmengine - INFO - Epoch(train) [11][ 120/1320] lr: 2.0000e-02 eta: 3:47:23 time: 0.2548 data_time: 0.0104 memory: 13708 grad_norm: 4.4328 loss: 2.0579 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0579 2023/02/18 00:09:58 - mmengine - INFO - Epoch(train) [11][ 140/1320] lr: 2.0000e-02 eta: 3:47:18 time: 0.2561 data_time: 0.0119 memory: 13708 grad_norm: 4.3624 loss: 2.0696 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0696 2023/02/18 00:10:03 - mmengine - INFO - Epoch(train) [11][ 160/1320] lr: 2.0000e-02 eta: 3:47:12 time: 0.2545 data_time: 0.0106 memory: 13708 grad_norm: 4.2670 loss: 2.1938 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.1938 2023/02/18 00:10:08 - mmengine - INFO - Epoch(train) [11][ 180/1320] lr: 2.0000e-02 eta: 3:47:07 time: 0.2544 data_time: 0.0105 memory: 13708 grad_norm: 4.3446 loss: 2.0486 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0486 2023/02/18 00:10:13 - mmengine - INFO - Epoch(train) [11][ 200/1320] lr: 2.0000e-02 eta: 3:47:01 time: 0.2547 data_time: 0.0105 memory: 13708 grad_norm: 4.4282 loss: 2.0956 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0956 2023/02/18 00:10:18 - mmengine - INFO - Epoch(train) [11][ 220/1320] lr: 2.0000e-02 eta: 3:46:56 time: 0.2577 data_time: 0.0125 memory: 13708 grad_norm: 4.3449 loss: 2.0948 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0948 2023/02/18 00:10:23 - mmengine - INFO - Epoch(train) [11][ 240/1320] lr: 2.0000e-02 eta: 3:46:50 time: 0.2538 data_time: 0.0101 memory: 13708 grad_norm: 4.2779 loss: 1.9641 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9641 2023/02/18 00:10:28 - mmengine - INFO - Epoch(train) [11][ 260/1320] lr: 2.0000e-02 eta: 3:46:45 time: 0.2569 data_time: 0.0123 memory: 13708 grad_norm: 4.2977 loss: 2.1399 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1399 2023/02/18 00:10:33 - mmengine - INFO - Epoch(train) [11][ 280/1320] lr: 2.0000e-02 eta: 3:46:39 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 4.2775 loss: 2.0869 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0869 2023/02/18 00:10:38 - mmengine - INFO - Epoch(train) [11][ 300/1320] lr: 2.0000e-02 eta: 3:46:34 time: 0.2540 data_time: 0.0102 memory: 13708 grad_norm: 4.4841 loss: 2.2311 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.2311 2023/02/18 00:10:44 - mmengine - INFO - Epoch(train) [11][ 320/1320] lr: 2.0000e-02 eta: 3:46:28 time: 0.2545 data_time: 0.0106 memory: 13708 grad_norm: 4.2170 loss: 2.3291 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.3291 2023/02/18 00:10:49 - mmengine - INFO - Epoch(train) [11][ 340/1320] lr: 2.0000e-02 eta: 3:46:23 time: 0.2547 data_time: 0.0101 memory: 13708 grad_norm: 4.2863 loss: 2.1827 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1827 2023/02/18 00:10:54 - mmengine - INFO - Epoch(train) [11][ 360/1320] lr: 2.0000e-02 eta: 3:46:17 time: 0.2548 data_time: 0.0102 memory: 13708 grad_norm: 4.2592 loss: 1.9170 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9170 2023/02/18 00:10:59 - mmengine - INFO - Epoch(train) [11][ 380/1320] lr: 2.0000e-02 eta: 3:46:12 time: 0.2558 data_time: 0.0115 memory: 13708 grad_norm: 4.3964 loss: 2.1294 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.1294 2023/02/18 00:11:04 - mmengine - INFO - Epoch(train) [11][ 400/1320] lr: 2.0000e-02 eta: 3:46:07 time: 0.2557 data_time: 0.0113 memory: 13708 grad_norm: 4.2964 loss: 1.9050 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9050 2023/02/18 00:11:09 - mmengine - INFO - Epoch(train) [11][ 420/1320] lr: 2.0000e-02 eta: 3:46:01 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.4235 loss: 2.1075 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1075 2023/02/18 00:11:14 - mmengine - INFO - Epoch(train) [11][ 440/1320] lr: 2.0000e-02 eta: 3:45:56 time: 0.2547 data_time: 0.0105 memory: 13708 grad_norm: 4.3958 loss: 2.0026 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.0026 2023/02/18 00:11:19 - mmengine - INFO - Epoch(train) [11][ 460/1320] lr: 2.0000e-02 eta: 3:45:50 time: 0.2544 data_time: 0.0105 memory: 13708 grad_norm: 4.3865 loss: 2.2019 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.2019 2023/02/18 00:11:24 - mmengine - INFO - Epoch(train) [11][ 480/1320] lr: 2.0000e-02 eta: 3:45:45 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.3637 loss: 2.1991 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.1991 2023/02/18 00:11:29 - mmengine - INFO - Epoch(train) [11][ 500/1320] lr: 2.0000e-02 eta: 3:45:39 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.5252 loss: 2.2608 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.2608 2023/02/18 00:11:35 - mmengine - INFO - Epoch(train) [11][ 520/1320] lr: 2.0000e-02 eta: 3:45:34 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.3980 loss: 2.2123 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.2123 2023/02/18 00:11:40 - mmengine - INFO - Epoch(train) [11][ 540/1320] lr: 2.0000e-02 eta: 3:45:28 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 4.3461 loss: 2.3281 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.3281 2023/02/18 00:11:45 - mmengine - INFO - Epoch(train) [11][ 560/1320] lr: 2.0000e-02 eta: 3:45:23 time: 0.2566 data_time: 0.0124 memory: 13708 grad_norm: 4.3497 loss: 2.2223 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.2223 2023/02/18 00:11:50 - mmengine - INFO - Epoch(train) [11][ 580/1320] lr: 2.0000e-02 eta: 3:45:17 time: 0.2550 data_time: 0.0104 memory: 13708 grad_norm: 4.4567 loss: 2.1807 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.1807 2023/02/18 00:11:55 - mmengine - INFO - Epoch(train) [11][ 600/1320] lr: 2.0000e-02 eta: 3:45:12 time: 0.2565 data_time: 0.0123 memory: 13708 grad_norm: 4.4217 loss: 2.0581 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0581 2023/02/18 00:12:01 - mmengine - INFO - Epoch(train) [11][ 620/1320] lr: 2.0000e-02 eta: 3:45:08 time: 0.2740 data_time: 0.0300 memory: 13708 grad_norm: 4.3908 loss: 2.1838 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1838 2023/02/18 00:12:06 - mmengine - INFO - Epoch(train) [11][ 640/1320] lr: 2.0000e-02 eta: 3:45:02 time: 0.2542 data_time: 0.0103 memory: 13708 grad_norm: 4.2688 loss: 2.1646 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1646 2023/02/18 00:12:11 - mmengine - INFO - Epoch(train) [11][ 660/1320] lr: 2.0000e-02 eta: 3:44:57 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 4.3271 loss: 2.2731 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.2731 2023/02/18 00:12:16 - mmengine - INFO - Epoch(train) [11][ 680/1320] lr: 2.0000e-02 eta: 3:44:52 time: 0.2568 data_time: 0.0119 memory: 13708 grad_norm: 4.4250 loss: 2.1734 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.1734 2023/02/18 00:12:21 - mmengine - INFO - Epoch(train) [11][ 700/1320] lr: 2.0000e-02 eta: 3:44:46 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.3541 loss: 2.3753 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3753 2023/02/18 00:12:26 - mmengine - INFO - Epoch(train) [11][ 720/1320] lr: 2.0000e-02 eta: 3:44:41 time: 0.2555 data_time: 0.0103 memory: 13708 grad_norm: 4.5942 loss: 2.1147 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.1147 2023/02/18 00:12:31 - mmengine - INFO - Epoch(train) [11][ 740/1320] lr: 2.0000e-02 eta: 3:44:35 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.3767 loss: 2.2289 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.2289 2023/02/18 00:12:36 - mmengine - INFO - Epoch(train) [11][ 760/1320] lr: 2.0000e-02 eta: 3:44:30 time: 0.2547 data_time: 0.0105 memory: 13708 grad_norm: 4.4046 loss: 2.1781 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.1781 2023/02/18 00:12:41 - mmengine - INFO - Epoch(train) [11][ 780/1320] lr: 2.0000e-02 eta: 3:44:24 time: 0.2545 data_time: 0.0103 memory: 13708 grad_norm: 4.3066 loss: 2.1589 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1589 2023/02/18 00:12:46 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:12:46 - mmengine - INFO - Epoch(train) [11][ 800/1320] lr: 2.0000e-02 eta: 3:44:19 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.4461 loss: 2.1147 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.1147 2023/02/18 00:12:52 - mmengine - INFO - Epoch(train) [11][ 820/1320] lr: 2.0000e-02 eta: 3:44:13 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 4.4376 loss: 2.1623 top1_acc: 0.2500 top5_acc: 0.3125 loss_cls: 2.1623 2023/02/18 00:12:57 - mmengine - INFO - Epoch(train) [11][ 840/1320] lr: 2.0000e-02 eta: 3:44:08 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.3861 loss: 2.1777 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.1777 2023/02/18 00:13:02 - mmengine - INFO - Epoch(train) [11][ 860/1320] lr: 2.0000e-02 eta: 3:44:02 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.3191 loss: 2.1537 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1537 2023/02/18 00:13:07 - mmengine - INFO - Epoch(train) [11][ 880/1320] lr: 2.0000e-02 eta: 3:43:57 time: 0.2548 data_time: 0.0102 memory: 13708 grad_norm: 4.3940 loss: 2.2986 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.2986 2023/02/18 00:13:12 - mmengine - INFO - Epoch(train) [11][ 900/1320] lr: 2.0000e-02 eta: 3:43:52 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.2606 loss: 2.2307 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.2307 2023/02/18 00:13:17 - mmengine - INFO - Epoch(train) [11][ 920/1320] lr: 2.0000e-02 eta: 3:43:46 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.3589 loss: 2.1971 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1971 2023/02/18 00:13:22 - mmengine - INFO - Epoch(train) [11][ 940/1320] lr: 2.0000e-02 eta: 3:43:41 time: 0.2545 data_time: 0.0100 memory: 13708 grad_norm: 4.4279 loss: 2.2891 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.2891 2023/02/18 00:13:27 - mmengine - INFO - Epoch(train) [11][ 960/1320] lr: 2.0000e-02 eta: 3:43:35 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.3415 loss: 2.3354 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.3354 2023/02/18 00:13:33 - mmengine - INFO - Epoch(train) [11][ 980/1320] lr: 2.0000e-02 eta: 3:43:30 time: 0.2652 data_time: 0.0204 memory: 13708 grad_norm: 4.2743 loss: 2.1448 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.1448 2023/02/18 00:13:38 - mmengine - INFO - Epoch(train) [11][1000/1320] lr: 2.0000e-02 eta: 3:43:25 time: 0.2543 data_time: 0.0099 memory: 13708 grad_norm: 4.2681 loss: 2.0651 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0651 2023/02/18 00:13:43 - mmengine - INFO - Epoch(train) [11][1020/1320] lr: 2.0000e-02 eta: 3:43:19 time: 0.2554 data_time: 0.0103 memory: 13708 grad_norm: 4.3255 loss: 2.0217 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0217 2023/02/18 00:13:48 - mmengine - INFO - Epoch(train) [11][1040/1320] lr: 2.0000e-02 eta: 3:43:14 time: 0.2549 data_time: 0.0103 memory: 13708 grad_norm: 4.3466 loss: 2.0056 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0056 2023/02/18 00:13:53 - mmengine - INFO - Epoch(train) [11][1060/1320] lr: 2.0000e-02 eta: 3:43:09 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.4268 loss: 2.2830 top1_acc: 0.2500 top5_acc: 0.3750 loss_cls: 2.2830 2023/02/18 00:13:58 - mmengine - INFO - Epoch(train) [11][1080/1320] lr: 2.0000e-02 eta: 3:43:03 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.2796 loss: 2.1428 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1428 2023/02/18 00:14:03 - mmengine - INFO - Epoch(train) [11][1100/1320] lr: 2.0000e-02 eta: 3:42:58 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.2974 loss: 2.0852 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0852 2023/02/18 00:14:08 - mmengine - INFO - Epoch(train) [11][1120/1320] lr: 2.0000e-02 eta: 3:42:52 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 4.3831 loss: 2.1614 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.1614 2023/02/18 00:14:13 - mmengine - INFO - Epoch(train) [11][1140/1320] lr: 2.0000e-02 eta: 3:42:47 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.3278 loss: 2.0794 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.0794 2023/02/18 00:14:18 - mmengine - INFO - Epoch(train) [11][1160/1320] lr: 2.0000e-02 eta: 3:42:41 time: 0.2547 data_time: 0.0105 memory: 13708 grad_norm: 4.4330 loss: 2.1066 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 2.1066 2023/02/18 00:14:24 - mmengine - INFO - Epoch(train) [11][1180/1320] lr: 2.0000e-02 eta: 3:42:36 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.4687 loss: 2.0308 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.0308 2023/02/18 00:14:29 - mmengine - INFO - Epoch(train) [11][1200/1320] lr: 2.0000e-02 eta: 3:42:30 time: 0.2549 data_time: 0.0100 memory: 13708 grad_norm: 4.3558 loss: 2.2672 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.2672 2023/02/18 00:14:34 - mmengine - INFO - Epoch(train) [11][1220/1320] lr: 2.0000e-02 eta: 3:42:25 time: 0.2549 data_time: 0.0101 memory: 13708 grad_norm: 4.2913 loss: 2.2192 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.2192 2023/02/18 00:14:39 - mmengine - INFO - Epoch(train) [11][1240/1320] lr: 2.0000e-02 eta: 3:42:19 time: 0.2545 data_time: 0.0103 memory: 13708 grad_norm: 4.3301 loss: 2.2008 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.2008 2023/02/18 00:14:44 - mmengine - INFO - Epoch(train) [11][1260/1320] lr: 2.0000e-02 eta: 3:42:14 time: 0.2556 data_time: 0.0114 memory: 13708 grad_norm: 4.3380 loss: 2.2393 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.2393 2023/02/18 00:14:49 - mmengine - INFO - Epoch(train) [11][1280/1320] lr: 2.0000e-02 eta: 3:42:09 time: 0.2567 data_time: 0.0124 memory: 13708 grad_norm: 4.2357 loss: 2.1074 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.1074 2023/02/18 00:14:54 - mmengine - INFO - Epoch(train) [11][1300/1320] lr: 2.0000e-02 eta: 3:42:03 time: 0.2552 data_time: 0.0110 memory: 13708 grad_norm: 4.2379 loss: 2.1353 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 2.1353 2023/02/18 00:14:59 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:14:59 - mmengine - INFO - Epoch(train) [11][1320/1320] lr: 2.0000e-02 eta: 3:41:58 time: 0.2504 data_time: 0.0101 memory: 13708 grad_norm: 4.4933 loss: 2.2906 top1_acc: 0.2727 top5_acc: 0.7273 loss_cls: 2.2906 2023/02/18 00:15:02 - mmengine - INFO - Epoch(val) [11][ 20/194] eta: 0:00:23 time: 0.1358 data_time: 0.0671 memory: 1818 2023/02/18 00:15:04 - mmengine - INFO - Epoch(val) [11][ 40/194] eta: 0:00:16 time: 0.0846 data_time: 0.0164 memory: 1818 2023/02/18 00:15:06 - mmengine - INFO - Epoch(val) [11][ 60/194] eta: 0:00:13 time: 0.0862 data_time: 0.0176 memory: 1818 2023/02/18 00:15:07 - mmengine - INFO - Epoch(val) [11][ 80/194] eta: 0:00:11 time: 0.0861 data_time: 0.0183 memory: 1818 2023/02/18 00:15:09 - mmengine - INFO - Epoch(val) [11][100/194] eta: 0:00:09 time: 0.0899 data_time: 0.0215 memory: 1818 2023/02/18 00:15:11 - mmengine - INFO - Epoch(val) [11][120/194] eta: 0:00:07 time: 0.0863 data_time: 0.0175 memory: 1818 2023/02/18 00:15:13 - mmengine - INFO - Epoch(val) [11][140/194] eta: 0:00:05 time: 0.0879 data_time: 0.0203 memory: 1818 2023/02/18 00:15:14 - mmengine - INFO - Epoch(val) [11][160/194] eta: 0:00:03 time: 0.0800 data_time: 0.0125 memory: 1818 2023/02/18 00:15:16 - mmengine - INFO - Epoch(val) [11][180/194] eta: 0:00:01 time: 0.0905 data_time: 0.0229 memory: 1818 2023/02/18 00:15:18 - mmengine - INFO - Epoch(val) [11][194/194] acc/top1: 0.4116 acc/top5: 0.7056 acc/mean1: 0.3509 2023/02/18 00:15:24 - mmengine - INFO - Epoch(train) [12][ 20/1320] lr: 2.0000e-02 eta: 3:41:56 time: 0.3060 data_time: 0.0431 memory: 13708 grad_norm: 4.2633 loss: 1.9316 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.9316 2023/02/18 00:15:29 - mmengine - INFO - Epoch(train) [12][ 40/1320] lr: 2.0000e-02 eta: 3:41:50 time: 0.2569 data_time: 0.0111 memory: 13708 grad_norm: 4.3182 loss: 2.1239 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.1239 2023/02/18 00:15:34 - mmengine - INFO - Epoch(train) [12][ 60/1320] lr: 2.0000e-02 eta: 3:41:45 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 4.3828 loss: 2.3045 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.3045 2023/02/18 00:15:39 - mmengine - INFO - Epoch(train) [12][ 80/1320] lr: 2.0000e-02 eta: 3:41:40 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 4.3346 loss: 2.0836 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0836 2023/02/18 00:15:44 - mmengine - INFO - Epoch(train) [12][ 100/1320] lr: 2.0000e-02 eta: 3:41:34 time: 0.2555 data_time: 0.0111 memory: 13708 grad_norm: 4.3197 loss: 2.1903 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.1903 2023/02/18 00:15:50 - mmengine - INFO - Epoch(train) [12][ 120/1320] lr: 2.0000e-02 eta: 3:41:29 time: 0.2558 data_time: 0.0111 memory: 13708 grad_norm: 4.5377 loss: 2.0268 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0268 2023/02/18 00:15:55 - mmengine - INFO - Epoch(train) [12][ 140/1320] lr: 2.0000e-02 eta: 3:41:23 time: 0.2561 data_time: 0.0115 memory: 13708 grad_norm: 4.3279 loss: 1.9935 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9935 2023/02/18 00:16:00 - mmengine - INFO - Epoch(train) [12][ 160/1320] lr: 2.0000e-02 eta: 3:41:18 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.3831 loss: 2.2205 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.2205 2023/02/18 00:16:05 - mmengine - INFO - Epoch(train) [12][ 180/1320] lr: 2.0000e-02 eta: 3:41:13 time: 0.2552 data_time: 0.0101 memory: 13708 grad_norm: 4.4860 loss: 2.2485 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.2485 2023/02/18 00:16:10 - mmengine - INFO - Epoch(train) [12][ 200/1320] lr: 2.0000e-02 eta: 3:41:07 time: 0.2544 data_time: 0.0101 memory: 13708 grad_norm: 4.5681 loss: 2.0152 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.0152 2023/02/18 00:16:15 - mmengine - INFO - Epoch(train) [12][ 220/1320] lr: 2.0000e-02 eta: 3:41:02 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.4461 loss: 2.2853 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.2853 2023/02/18 00:16:20 - mmengine - INFO - Epoch(train) [12][ 240/1320] lr: 2.0000e-02 eta: 3:40:56 time: 0.2545 data_time: 0.0103 memory: 13708 grad_norm: 4.2739 loss: 2.0829 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0829 2023/02/18 00:16:25 - mmengine - INFO - Epoch(train) [12][ 260/1320] lr: 2.0000e-02 eta: 3:40:51 time: 0.2544 data_time: 0.0102 memory: 13708 grad_norm: 4.3055 loss: 1.9127 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.9127 2023/02/18 00:16:30 - mmengine - INFO - Epoch(train) [12][ 280/1320] lr: 2.0000e-02 eta: 3:40:45 time: 0.2556 data_time: 0.0103 memory: 13708 grad_norm: 4.3382 loss: 2.0895 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0895 2023/02/18 00:16:35 - mmengine - INFO - Epoch(train) [12][ 300/1320] lr: 2.0000e-02 eta: 3:40:40 time: 0.2550 data_time: 0.0111 memory: 13708 grad_norm: 4.3692 loss: 2.0861 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0861 2023/02/18 00:16:41 - mmengine - INFO - Epoch(train) [12][ 320/1320] lr: 2.0000e-02 eta: 3:40:34 time: 0.2544 data_time: 0.0105 memory: 13708 grad_norm: 4.4204 loss: 2.1927 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1927 2023/02/18 00:16:46 - mmengine - INFO - Epoch(train) [12][ 340/1320] lr: 2.0000e-02 eta: 3:40:29 time: 0.2548 data_time: 0.0103 memory: 13708 grad_norm: 4.3754 loss: 2.1724 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.1724 2023/02/18 00:16:51 - mmengine - INFO - Epoch(train) [12][ 360/1320] lr: 2.0000e-02 eta: 3:40:24 time: 0.2548 data_time: 0.0109 memory: 13708 grad_norm: 4.3597 loss: 2.1104 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1104 2023/02/18 00:16:56 - mmengine - INFO - Epoch(train) [12][ 380/1320] lr: 2.0000e-02 eta: 3:40:18 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.2397 loss: 1.9032 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.9032 2023/02/18 00:17:01 - mmengine - INFO - Epoch(train) [12][ 400/1320] lr: 2.0000e-02 eta: 3:40:13 time: 0.2548 data_time: 0.0103 memory: 13708 grad_norm: 4.4651 loss: 2.1576 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1576 2023/02/18 00:17:06 - mmengine - INFO - Epoch(train) [12][ 420/1320] lr: 2.0000e-02 eta: 3:40:07 time: 0.2544 data_time: 0.0102 memory: 13708 grad_norm: 4.4214 loss: 2.3255 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.3255 2023/02/18 00:17:11 - mmengine - INFO - Epoch(train) [12][ 440/1320] lr: 2.0000e-02 eta: 3:40:02 time: 0.2543 data_time: 0.0102 memory: 13708 grad_norm: 4.3780 loss: 2.1970 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1970 2023/02/18 00:17:16 - mmengine - INFO - Epoch(train) [12][ 460/1320] lr: 2.0000e-02 eta: 3:39:56 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.2359 loss: 2.1443 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.1443 2023/02/18 00:17:21 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:17:21 - mmengine - INFO - Epoch(train) [12][ 480/1320] lr: 2.0000e-02 eta: 3:39:51 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 4.4010 loss: 2.1450 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.1450 2023/02/18 00:17:26 - mmengine - INFO - Epoch(train) [12][ 500/1320] lr: 2.0000e-02 eta: 3:39:45 time: 0.2545 data_time: 0.0106 memory: 13708 grad_norm: 4.3941 loss: 2.1630 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.1630 2023/02/18 00:17:32 - mmengine - INFO - Epoch(train) [12][ 520/1320] lr: 2.0000e-02 eta: 3:39:40 time: 0.2563 data_time: 0.0123 memory: 13708 grad_norm: 4.4029 loss: 2.0079 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.0079 2023/02/18 00:17:37 - mmengine - INFO - Epoch(train) [12][ 540/1320] lr: 2.0000e-02 eta: 3:39:35 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.4114 loss: 2.0772 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0772 2023/02/18 00:17:42 - mmengine - INFO - Epoch(train) [12][ 560/1320] lr: 2.0000e-02 eta: 3:39:29 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 4.3929 loss: 1.8412 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8412 2023/02/18 00:17:47 - mmengine - INFO - Epoch(train) [12][ 580/1320] lr: 2.0000e-02 eta: 3:39:24 time: 0.2550 data_time: 0.0101 memory: 13708 grad_norm: 4.3954 loss: 1.9703 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9703 2023/02/18 00:17:52 - mmengine - INFO - Epoch(train) [12][ 600/1320] lr: 2.0000e-02 eta: 3:39:18 time: 0.2546 data_time: 0.0103 memory: 13708 grad_norm: 4.4745 loss: 2.1976 top1_acc: 0.5000 top5_acc: 0.5625 loss_cls: 2.1976 2023/02/18 00:17:57 - mmengine - INFO - Epoch(train) [12][ 620/1320] lr: 2.0000e-02 eta: 3:39:13 time: 0.2546 data_time: 0.0105 memory: 13708 grad_norm: 4.3965 loss: 1.9823 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 1.9823 2023/02/18 00:18:02 - mmengine - INFO - Epoch(train) [12][ 640/1320] lr: 2.0000e-02 eta: 3:39:08 time: 0.2544 data_time: 0.0101 memory: 13708 grad_norm: 4.4102 loss: 2.0365 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.0365 2023/02/18 00:18:07 - mmengine - INFO - Epoch(train) [12][ 660/1320] lr: 2.0000e-02 eta: 3:39:02 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.3364 loss: 2.1320 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.1320 2023/02/18 00:18:12 - mmengine - INFO - Epoch(train) [12][ 680/1320] lr: 2.0000e-02 eta: 3:38:57 time: 0.2546 data_time: 0.0101 memory: 13708 grad_norm: 4.4018 loss: 2.2874 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.2874 2023/02/18 00:18:17 - mmengine - INFO - Epoch(train) [12][ 700/1320] lr: 2.0000e-02 eta: 3:38:51 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.4220 loss: 2.1339 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1339 2023/02/18 00:18:23 - mmengine - INFO - Epoch(train) [12][ 720/1320] lr: 2.0000e-02 eta: 3:38:46 time: 0.2546 data_time: 0.0105 memory: 13708 grad_norm: 4.3565 loss: 2.0853 top1_acc: 0.1250 top5_acc: 0.6250 loss_cls: 2.0853 2023/02/18 00:18:28 - mmengine - INFO - Epoch(train) [12][ 740/1320] lr: 2.0000e-02 eta: 3:38:40 time: 0.2548 data_time: 0.0103 memory: 13708 grad_norm: 4.3867 loss: 2.0792 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0792 2023/02/18 00:18:33 - mmengine - INFO - Epoch(train) [12][ 760/1320] lr: 2.0000e-02 eta: 3:38:35 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.3030 loss: 2.1430 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1430 2023/02/18 00:18:38 - mmengine - INFO - Epoch(train) [12][ 780/1320] lr: 2.0000e-02 eta: 3:38:30 time: 0.2549 data_time: 0.0102 memory: 13708 grad_norm: 4.4321 loss: 2.1464 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1464 2023/02/18 00:18:43 - mmengine - INFO - Epoch(train) [12][ 800/1320] lr: 2.0000e-02 eta: 3:38:24 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 4.4314 loss: 2.2272 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.2272 2023/02/18 00:18:48 - mmengine - INFO - Epoch(train) [12][ 820/1320] lr: 2.0000e-02 eta: 3:38:19 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 4.2228 loss: 2.0717 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0717 2023/02/18 00:18:53 - mmengine - INFO - Epoch(train) [12][ 840/1320] lr: 2.0000e-02 eta: 3:38:13 time: 0.2550 data_time: 0.0099 memory: 13708 grad_norm: 4.3462 loss: 2.3433 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.3433 2023/02/18 00:18:58 - mmengine - INFO - Epoch(train) [12][ 860/1320] lr: 2.0000e-02 eta: 3:38:08 time: 0.2551 data_time: 0.0107 memory: 13708 grad_norm: 4.2292 loss: 1.9658 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9658 2023/02/18 00:19:03 - mmengine - INFO - Epoch(train) [12][ 880/1320] lr: 2.0000e-02 eta: 3:38:03 time: 0.2546 data_time: 0.0103 memory: 13708 grad_norm: 4.4001 loss: 2.1674 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.1674 2023/02/18 00:19:08 - mmengine - INFO - Epoch(train) [12][ 900/1320] lr: 2.0000e-02 eta: 3:37:57 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.3249 loss: 2.1817 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1817 2023/02/18 00:19:14 - mmengine - INFO - Epoch(train) [12][ 920/1320] lr: 2.0000e-02 eta: 3:37:52 time: 0.2552 data_time: 0.0105 memory: 13708 grad_norm: 4.3021 loss: 2.1298 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1298 2023/02/18 00:19:19 - mmengine - INFO - Epoch(train) [12][ 940/1320] lr: 2.0000e-02 eta: 3:37:46 time: 0.2545 data_time: 0.0107 memory: 13708 grad_norm: 4.2943 loss: 2.0327 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0327 2023/02/18 00:19:24 - mmengine - INFO - Epoch(train) [12][ 960/1320] lr: 2.0000e-02 eta: 3:37:41 time: 0.2544 data_time: 0.0104 memory: 13708 grad_norm: 4.4259 loss: 2.0700 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.0700 2023/02/18 00:19:29 - mmengine - INFO - Epoch(train) [12][ 980/1320] lr: 2.0000e-02 eta: 3:37:36 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 4.3092 loss: 2.0400 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0400 2023/02/18 00:19:34 - mmengine - INFO - Epoch(train) [12][1000/1320] lr: 2.0000e-02 eta: 3:37:30 time: 0.2553 data_time: 0.0116 memory: 13708 grad_norm: 4.3750 loss: 2.0410 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0410 2023/02/18 00:19:39 - mmengine - INFO - Epoch(train) [12][1020/1320] lr: 2.0000e-02 eta: 3:37:25 time: 0.2565 data_time: 0.0124 memory: 13708 grad_norm: 4.4038 loss: 2.0529 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0529 2023/02/18 00:19:44 - mmengine - INFO - Epoch(train) [12][1040/1320] lr: 2.0000e-02 eta: 3:37:19 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 4.2714 loss: 2.1860 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1860 2023/02/18 00:19:49 - mmengine - INFO - Epoch(train) [12][1060/1320] lr: 2.0000e-02 eta: 3:37:14 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.4187 loss: 2.0163 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 2.0163 2023/02/18 00:19:55 - mmengine - INFO - Epoch(train) [12][1080/1320] lr: 2.0000e-02 eta: 3:37:10 time: 0.2742 data_time: 0.0305 memory: 13708 grad_norm: 4.3456 loss: 2.1653 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.1653 2023/02/18 00:20:00 - mmengine - INFO - Epoch(train) [12][1100/1320] lr: 2.0000e-02 eta: 3:37:04 time: 0.2546 data_time: 0.0104 memory: 13708 grad_norm: 4.3302 loss: 2.3169 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 2.3169 2023/02/18 00:20:05 - mmengine - INFO - Epoch(train) [12][1120/1320] lr: 2.0000e-02 eta: 3:36:59 time: 0.2549 data_time: 0.0102 memory: 13708 grad_norm: 4.3721 loss: 2.1278 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.1278 2023/02/18 00:20:10 - mmengine - INFO - Epoch(train) [12][1140/1320] lr: 2.0000e-02 eta: 3:36:54 time: 0.2551 data_time: 0.0103 memory: 13708 grad_norm: 4.4052 loss: 2.2031 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2031 2023/02/18 00:20:15 - mmengine - INFO - Epoch(train) [12][1160/1320] lr: 2.0000e-02 eta: 3:36:48 time: 0.2546 data_time: 0.0102 memory: 13708 grad_norm: 4.3614 loss: 1.9805 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.9805 2023/02/18 00:20:20 - mmengine - INFO - Epoch(train) [12][1180/1320] lr: 2.0000e-02 eta: 3:36:43 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.4105 loss: 2.0312 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 2.0312 2023/02/18 00:20:25 - mmengine - INFO - Epoch(train) [12][1200/1320] lr: 2.0000e-02 eta: 3:36:37 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.3938 loss: 1.9931 top1_acc: 0.5000 top5_acc: 0.5000 loss_cls: 1.9931 2023/02/18 00:20:30 - mmengine - INFO - Epoch(train) [12][1220/1320] lr: 2.0000e-02 eta: 3:36:32 time: 0.2541 data_time: 0.0103 memory: 13708 grad_norm: 4.4344 loss: 2.2625 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.2625 2023/02/18 00:20:36 - mmengine - INFO - Epoch(train) [12][1240/1320] lr: 2.0000e-02 eta: 3:36:27 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.4485 loss: 2.2044 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2044 2023/02/18 00:20:41 - mmengine - INFO - Epoch(train) [12][1260/1320] lr: 2.0000e-02 eta: 3:36:21 time: 0.2550 data_time: 0.0102 memory: 13708 grad_norm: 4.3126 loss: 2.0048 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.0048 2023/02/18 00:20:46 - mmengine - INFO - Epoch(train) [12][1280/1320] lr: 2.0000e-02 eta: 3:36:16 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.4811 loss: 2.1460 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.1460 2023/02/18 00:20:51 - mmengine - INFO - Epoch(train) [12][1300/1320] lr: 2.0000e-02 eta: 3:36:10 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 4.3564 loss: 2.1293 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 2.1293 2023/02/18 00:20:56 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:20:56 - mmengine - INFO - Epoch(train) [12][1320/1320] lr: 2.0000e-02 eta: 3:36:05 time: 0.2507 data_time: 0.0103 memory: 13708 grad_norm: 4.2841 loss: 2.1955 top1_acc: 0.1818 top5_acc: 0.6364 loss_cls: 2.1955 2023/02/18 00:20:56 - mmengine - INFO - Saving checkpoint at 12 epochs 2023/02/18 00:21:00 - mmengine - INFO - Epoch(val) [12][ 20/194] eta: 0:00:22 time: 0.1266 data_time: 0.0579 memory: 1818 2023/02/18 00:21:01 - mmengine - INFO - Epoch(val) [12][ 40/194] eta: 0:00:16 time: 0.0841 data_time: 0.0162 memory: 1818 2023/02/18 00:21:03 - mmengine - INFO - Epoch(val) [12][ 60/194] eta: 0:00:13 time: 0.0894 data_time: 0.0211 memory: 1818 2023/02/18 00:21:05 - mmengine - INFO - Epoch(val) [12][ 80/194] eta: 0:00:10 time: 0.0843 data_time: 0.0166 memory: 1818 2023/02/18 00:21:07 - mmengine - INFO - Epoch(val) [12][100/194] eta: 0:00:08 time: 0.0902 data_time: 0.0223 memory: 1818 2023/02/18 00:21:08 - mmengine - INFO - Epoch(val) [12][120/194] eta: 0:00:06 time: 0.0843 data_time: 0.0167 memory: 1818 2023/02/18 00:21:10 - mmengine - INFO - Epoch(val) [12][140/194] eta: 0:00:05 time: 0.0964 data_time: 0.0284 memory: 1818 2023/02/18 00:21:12 - mmengine - INFO - Epoch(val) [12][160/194] eta: 0:00:03 time: 0.0817 data_time: 0.0130 memory: 1818 2023/02/18 00:21:13 - mmengine - INFO - Epoch(val) [12][180/194] eta: 0:00:01 time: 0.0812 data_time: 0.0156 memory: 1818 2023/02/18 00:21:15 - mmengine - INFO - Epoch(val) [12][194/194] acc/top1: 0.4257 acc/top5: 0.7302 acc/mean1: 0.3552 2023/02/18 00:21:21 - mmengine - INFO - Epoch(train) [13][ 20/1320] lr: 2.0000e-02 eta: 3:36:02 time: 0.2950 data_time: 0.0428 memory: 13708 grad_norm: 4.3602 loss: 2.1203 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.1203 2023/02/18 00:21:26 - mmengine - INFO - Epoch(train) [13][ 40/1320] lr: 2.0000e-02 eta: 3:35:57 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.4593 loss: 2.1487 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.1487 2023/02/18 00:21:31 - mmengine - INFO - Epoch(train) [13][ 60/1320] lr: 2.0000e-02 eta: 3:35:51 time: 0.2548 data_time: 0.0099 memory: 13708 grad_norm: 4.4260 loss: 2.3502 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.3502 2023/02/18 00:21:36 - mmengine - INFO - Epoch(train) [13][ 80/1320] lr: 2.0000e-02 eta: 3:35:46 time: 0.2549 data_time: 0.0100 memory: 13708 grad_norm: 4.2399 loss: 2.0582 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 2.0582 2023/02/18 00:21:41 - mmengine - INFO - Epoch(train) [13][ 100/1320] lr: 2.0000e-02 eta: 3:35:40 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.3682 loss: 2.1108 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 2.1108 2023/02/18 00:21:47 - mmengine - INFO - Epoch(train) [13][ 120/1320] lr: 2.0000e-02 eta: 3:35:35 time: 0.2550 data_time: 0.0102 memory: 13708 grad_norm: 4.4617 loss: 1.9481 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 1.9481 2023/02/18 00:21:52 - mmengine - INFO - Epoch(train) [13][ 140/1320] lr: 2.0000e-02 eta: 3:35:30 time: 0.2549 data_time: 0.0098 memory: 13708 grad_norm: 4.3406 loss: 2.1392 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 2.1392 2023/02/18 00:21:57 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:21:57 - mmengine - INFO - Epoch(train) [13][ 160/1320] lr: 2.0000e-02 eta: 3:35:24 time: 0.2546 data_time: 0.0106 memory: 13708 grad_norm: 4.3850 loss: 1.9922 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9922 2023/02/18 00:22:02 - mmengine - INFO - Epoch(train) [13][ 180/1320] lr: 2.0000e-02 eta: 3:35:19 time: 0.2545 data_time: 0.0101 memory: 13708 grad_norm: 4.2481 loss: 2.0475 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0475 2023/02/18 00:22:07 - mmengine - INFO - Epoch(train) [13][ 200/1320] lr: 2.0000e-02 eta: 3:35:13 time: 0.2541 data_time: 0.0103 memory: 13708 grad_norm: 4.3324 loss: 2.1383 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.1383 2023/02/18 00:22:12 - mmengine - INFO - Epoch(train) [13][ 220/1320] lr: 2.0000e-02 eta: 3:35:08 time: 0.2546 data_time: 0.0102 memory: 13708 grad_norm: 4.3894 loss: 2.0883 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.0883 2023/02/18 00:22:17 - mmengine - INFO - Epoch(train) [13][ 240/1320] lr: 2.0000e-02 eta: 3:35:02 time: 0.2545 data_time: 0.0107 memory: 13708 grad_norm: 4.3400 loss: 1.9800 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 1.9800 2023/02/18 00:22:22 - mmengine - INFO - Epoch(train) [13][ 260/1320] lr: 2.0000e-02 eta: 3:34:57 time: 0.2548 data_time: 0.0109 memory: 13708 grad_norm: 4.3600 loss: 2.0795 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0795 2023/02/18 00:22:27 - mmengine - INFO - Epoch(train) [13][ 280/1320] lr: 2.0000e-02 eta: 3:34:52 time: 0.2544 data_time: 0.0101 memory: 13708 grad_norm: 4.3801 loss: 2.1260 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 2.1260 2023/02/18 00:22:32 - mmengine - INFO - Epoch(train) [13][ 300/1320] lr: 2.0000e-02 eta: 3:34:46 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.2763 loss: 2.1152 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.1152 2023/02/18 00:22:38 - mmengine - INFO - Epoch(train) [13][ 320/1320] lr: 2.0000e-02 eta: 3:34:41 time: 0.2542 data_time: 0.0104 memory: 13708 grad_norm: 4.4102 loss: 2.3329 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.3329 2023/02/18 00:22:43 - mmengine - INFO - Epoch(train) [13][ 340/1320] lr: 2.0000e-02 eta: 3:34:36 time: 0.2567 data_time: 0.0117 memory: 13708 grad_norm: 4.2662 loss: 2.1003 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.1003 2023/02/18 00:22:48 - mmengine - INFO - Epoch(train) [13][ 360/1320] lr: 2.0000e-02 eta: 3:34:30 time: 0.2561 data_time: 0.0112 memory: 13708 grad_norm: 4.3848 loss: 2.1930 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.1930 2023/02/18 00:22:53 - mmengine - INFO - Epoch(train) [13][ 380/1320] lr: 2.0000e-02 eta: 3:34:25 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.4928 loss: 2.2759 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.2759 2023/02/18 00:22:58 - mmengine - INFO - Epoch(train) [13][ 400/1320] lr: 2.0000e-02 eta: 3:34:20 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 4.3208 loss: 2.2776 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2776 2023/02/18 00:23:03 - mmengine - INFO - Epoch(train) [13][ 420/1320] lr: 2.0000e-02 eta: 3:34:14 time: 0.2544 data_time: 0.0103 memory: 13708 grad_norm: 4.4900 loss: 2.0248 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.0248 2023/02/18 00:23:08 - mmengine - INFO - Epoch(train) [13][ 440/1320] lr: 2.0000e-02 eta: 3:34:09 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.2488 loss: 1.9668 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 1.9668 2023/02/18 00:23:13 - mmengine - INFO - Epoch(train) [13][ 460/1320] lr: 2.0000e-02 eta: 3:34:03 time: 0.2566 data_time: 0.0115 memory: 13708 grad_norm: 4.3687 loss: 2.0506 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0506 2023/02/18 00:23:18 - mmengine - INFO - Epoch(train) [13][ 480/1320] lr: 2.0000e-02 eta: 3:33:58 time: 0.2547 data_time: 0.0099 memory: 13708 grad_norm: 4.5716 loss: 2.1280 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.1280 2023/02/18 00:23:23 - mmengine - INFO - Epoch(train) [13][ 500/1320] lr: 2.0000e-02 eta: 3:33:53 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 4.3514 loss: 2.0144 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 2.0144 2023/02/18 00:23:29 - mmengine - INFO - Epoch(train) [13][ 520/1320] lr: 2.0000e-02 eta: 3:33:47 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.3815 loss: 2.2598 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.2598 2023/02/18 00:23:34 - mmengine - INFO - Epoch(train) [13][ 540/1320] lr: 2.0000e-02 eta: 3:33:42 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 4.2478 loss: 2.1936 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.1936 2023/02/18 00:23:39 - mmengine - INFO - Epoch(train) [13][ 560/1320] lr: 2.0000e-02 eta: 3:33:36 time: 0.2547 data_time: 0.0102 memory: 13708 grad_norm: 4.2707 loss: 2.0739 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0739 2023/02/18 00:23:44 - mmengine - INFO - Epoch(train) [13][ 580/1320] lr: 2.0000e-02 eta: 3:33:31 time: 0.2545 data_time: 0.0103 memory: 13708 grad_norm: 4.2527 loss: 2.2002 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.2002 2023/02/18 00:23:49 - mmengine - INFO - Epoch(train) [13][ 600/1320] lr: 2.0000e-02 eta: 3:33:26 time: 0.2544 data_time: 0.0102 memory: 13708 grad_norm: 4.2952 loss: 1.8501 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8501 2023/02/18 00:23:54 - mmengine - INFO - Epoch(train) [13][ 620/1320] lr: 2.0000e-02 eta: 3:33:20 time: 0.2552 data_time: 0.0103 memory: 13708 grad_norm: 4.4624 loss: 2.1032 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.1032 2023/02/18 00:23:59 - mmengine - INFO - Epoch(train) [13][ 640/1320] lr: 2.0000e-02 eta: 3:33:15 time: 0.2542 data_time: 0.0101 memory: 13708 grad_norm: 4.3899 loss: 2.1621 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 2.1621 2023/02/18 00:24:04 - mmengine - INFO - Epoch(train) [13][ 660/1320] lr: 2.0000e-02 eta: 3:33:09 time: 0.2543 data_time: 0.0106 memory: 13708 grad_norm: 4.3984 loss: 1.8506 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8506 2023/02/18 00:24:09 - mmengine - INFO - Epoch(train) [13][ 680/1320] lr: 2.0000e-02 eta: 3:33:04 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.4494 loss: 2.0633 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0633 2023/02/18 00:24:14 - mmengine - INFO - Epoch(train) [13][ 700/1320] lr: 2.0000e-02 eta: 3:32:59 time: 0.2543 data_time: 0.0102 memory: 13708 grad_norm: 4.3196 loss: 2.0138 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.0138 2023/02/18 00:24:20 - mmengine - INFO - Epoch(train) [13][ 720/1320] lr: 2.0000e-02 eta: 3:32:53 time: 0.2539 data_time: 0.0106 memory: 13708 grad_norm: 4.3825 loss: 1.9970 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9970 2023/02/18 00:24:25 - mmengine - INFO - Epoch(train) [13][ 740/1320] lr: 2.0000e-02 eta: 3:32:48 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 4.2620 loss: 1.9235 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9235 2023/02/18 00:24:30 - mmengine - INFO - Epoch(train) [13][ 760/1320] lr: 2.0000e-02 eta: 3:32:43 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 4.4693 loss: 2.0852 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.0852 2023/02/18 00:24:35 - mmengine - INFO - Epoch(train) [13][ 780/1320] lr: 2.0000e-02 eta: 3:32:37 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.4798 loss: 1.8268 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 1.8268 2023/02/18 00:24:40 - mmengine - INFO - Epoch(train) [13][ 800/1320] lr: 2.0000e-02 eta: 3:32:32 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 4.3818 loss: 2.0251 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0251 2023/02/18 00:24:45 - mmengine - INFO - Epoch(train) [13][ 820/1320] lr: 2.0000e-02 eta: 3:32:27 time: 0.2556 data_time: 0.0115 memory: 13708 grad_norm: 4.3897 loss: 2.0993 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0993 2023/02/18 00:24:50 - mmengine - INFO - Epoch(train) [13][ 840/1320] lr: 2.0000e-02 eta: 3:32:21 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.2709 loss: 2.1582 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.1582 2023/02/18 00:24:55 - mmengine - INFO - Epoch(train) [13][ 860/1320] lr: 2.0000e-02 eta: 3:32:16 time: 0.2543 data_time: 0.0104 memory: 13708 grad_norm: 4.2315 loss: 2.1462 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.1462 2023/02/18 00:25:00 - mmengine - INFO - Epoch(train) [13][ 880/1320] lr: 2.0000e-02 eta: 3:32:10 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.4364 loss: 1.9991 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9991 2023/02/18 00:25:05 - mmengine - INFO - Epoch(train) [13][ 900/1320] lr: 2.0000e-02 eta: 3:32:05 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.5163 loss: 2.0663 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0663 2023/02/18 00:25:11 - mmengine - INFO - Epoch(train) [13][ 920/1320] lr: 2.0000e-02 eta: 3:32:00 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.3540 loss: 1.8727 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8727 2023/02/18 00:25:16 - mmengine - INFO - Epoch(train) [13][ 940/1320] lr: 2.0000e-02 eta: 3:31:54 time: 0.2552 data_time: 0.0105 memory: 13708 grad_norm: 4.4247 loss: 2.0228 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 2.0228 2023/02/18 00:25:21 - mmengine - INFO - Epoch(train) [13][ 960/1320] lr: 2.0000e-02 eta: 3:31:49 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.4437 loss: 2.1571 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.1571 2023/02/18 00:25:26 - mmengine - INFO - Epoch(train) [13][ 980/1320] lr: 2.0000e-02 eta: 3:31:44 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.1873 loss: 2.1102 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.1102 2023/02/18 00:25:31 - mmengine - INFO - Epoch(train) [13][1000/1320] lr: 2.0000e-02 eta: 3:31:38 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.2786 loss: 2.0834 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.0834 2023/02/18 00:25:36 - mmengine - INFO - Epoch(train) [13][1020/1320] lr: 2.0000e-02 eta: 3:31:33 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.3121 loss: 2.0583 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0583 2023/02/18 00:25:41 - mmengine - INFO - Epoch(train) [13][1040/1320] lr: 2.0000e-02 eta: 3:31:28 time: 0.2556 data_time: 0.0111 memory: 13708 grad_norm: 4.2093 loss: 2.1326 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1326 2023/02/18 00:25:46 - mmengine - INFO - Epoch(train) [13][1060/1320] lr: 2.0000e-02 eta: 3:31:22 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.1416 loss: 2.0340 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0340 2023/02/18 00:25:51 - mmengine - INFO - Epoch(train) [13][1080/1320] lr: 2.0000e-02 eta: 3:31:17 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.3048 loss: 2.0351 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.0351 2023/02/18 00:25:56 - mmengine - INFO - Epoch(train) [13][1100/1320] lr: 2.0000e-02 eta: 3:31:11 time: 0.2546 data_time: 0.0106 memory: 13708 grad_norm: 4.2618 loss: 2.1153 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.1153 2023/02/18 00:26:02 - mmengine - INFO - Epoch(train) [13][1120/1320] lr: 2.0000e-02 eta: 3:31:06 time: 0.2544 data_time: 0.0103 memory: 13708 grad_norm: 4.3003 loss: 2.2378 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.2378 2023/02/18 00:26:07 - mmengine - INFO - Epoch(train) [13][1140/1320] lr: 2.0000e-02 eta: 3:31:01 time: 0.2551 data_time: 0.0107 memory: 13708 grad_norm: 4.3141 loss: 2.0392 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0392 2023/02/18 00:26:12 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:26:12 - mmengine - INFO - Epoch(train) [13][1160/1320] lr: 2.0000e-02 eta: 3:30:55 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.1947 loss: 2.1720 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1720 2023/02/18 00:26:17 - mmengine - INFO - Epoch(train) [13][1180/1320] lr: 2.0000e-02 eta: 3:30:50 time: 0.2542 data_time: 0.0101 memory: 13708 grad_norm: 4.3595 loss: 2.0268 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0268 2023/02/18 00:26:22 - mmengine - INFO - Epoch(train) [13][1200/1320] lr: 2.0000e-02 eta: 3:30:45 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.3506 loss: 2.1215 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1215 2023/02/18 00:26:27 - mmengine - INFO - Epoch(train) [13][1220/1320] lr: 2.0000e-02 eta: 3:30:39 time: 0.2546 data_time: 0.0102 memory: 13708 grad_norm: 4.3170 loss: 2.0607 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0607 2023/02/18 00:26:32 - mmengine - INFO - Epoch(train) [13][1240/1320] lr: 2.0000e-02 eta: 3:30:34 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.4424 loss: 2.2272 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.2272 2023/02/18 00:26:37 - mmengine - INFO - Epoch(train) [13][1260/1320] lr: 2.0000e-02 eta: 3:30:29 time: 0.2549 data_time: 0.0104 memory: 13708 grad_norm: 4.3342 loss: 2.2400 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.2400 2023/02/18 00:26:42 - mmengine - INFO - Epoch(train) [13][1280/1320] lr: 2.0000e-02 eta: 3:30:23 time: 0.2546 data_time: 0.0105 memory: 13708 grad_norm: 4.3573 loss: 1.8978 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8978 2023/02/18 00:26:47 - mmengine - INFO - Epoch(train) [13][1300/1320] lr: 2.0000e-02 eta: 3:30:18 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.3092 loss: 2.0280 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0280 2023/02/18 00:26:52 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:26:52 - mmengine - INFO - Epoch(train) [13][1320/1320] lr: 2.0000e-02 eta: 3:30:12 time: 0.2509 data_time: 0.0104 memory: 13708 grad_norm: 4.4728 loss: 2.0155 top1_acc: 0.7273 top5_acc: 0.8182 loss_cls: 2.0155 2023/02/18 00:26:55 - mmengine - INFO - Epoch(val) [13][ 20/194] eta: 0:00:21 time: 0.1237 data_time: 0.0556 memory: 1818 2023/02/18 00:26:57 - mmengine - INFO - Epoch(val) [13][ 40/194] eta: 0:00:16 time: 0.0854 data_time: 0.0178 memory: 1818 2023/02/18 00:26:58 - mmengine - INFO - Epoch(val) [13][ 60/194] eta: 0:00:13 time: 0.0912 data_time: 0.0235 memory: 1818 2023/02/18 00:27:00 - mmengine - INFO - Epoch(val) [13][ 80/194] eta: 0:00:10 time: 0.0845 data_time: 0.0169 memory: 1818 2023/02/18 00:27:02 - mmengine - INFO - Epoch(val) [13][100/194] eta: 0:00:08 time: 0.0902 data_time: 0.0220 memory: 1818 2023/02/18 00:27:04 - mmengine - INFO - Epoch(val) [13][120/194] eta: 0:00:06 time: 0.0849 data_time: 0.0163 memory: 1818 2023/02/18 00:27:05 - mmengine - INFO - Epoch(val) [13][140/194] eta: 0:00:04 time: 0.0881 data_time: 0.0197 memory: 1818 2023/02/18 00:27:07 - mmengine - INFO - Epoch(val) [13][160/194] eta: 0:00:03 time: 0.0808 data_time: 0.0134 memory: 1818 2023/02/18 00:27:09 - mmengine - INFO - Epoch(val) [13][180/194] eta: 0:00:01 time: 0.0863 data_time: 0.0177 memory: 1818 2023/02/18 00:27:11 - mmengine - INFO - Epoch(val) [13][194/194] acc/top1: 0.4345 acc/top5: 0.7348 acc/mean1: 0.3676 2023/02/18 00:27:11 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_10.pth is removed 2023/02/18 00:27:12 - mmengine - INFO - The best checkpoint with 0.4345 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2023/02/18 00:27:18 - mmengine - INFO - Epoch(train) [14][ 20/1320] lr: 2.0000e-02 eta: 3:30:09 time: 0.2972 data_time: 0.0427 memory: 13708 grad_norm: 4.5041 loss: 2.1271 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.1271 2023/02/18 00:27:23 - mmengine - INFO - Epoch(train) [14][ 40/1320] lr: 2.0000e-02 eta: 3:30:04 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.3765 loss: 2.0044 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0044 2023/02/18 00:27:28 - mmengine - INFO - Epoch(train) [14][ 60/1320] lr: 2.0000e-02 eta: 3:29:59 time: 0.2542 data_time: 0.0100 memory: 13708 grad_norm: 4.2925 loss: 2.2572 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.2572 2023/02/18 00:27:33 - mmengine - INFO - Epoch(train) [14][ 80/1320] lr: 2.0000e-02 eta: 3:29:53 time: 0.2547 data_time: 0.0096 memory: 13708 grad_norm: 4.4345 loss: 2.1003 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.1003 2023/02/18 00:27:38 - mmengine - INFO - Epoch(train) [14][ 100/1320] lr: 2.0000e-02 eta: 3:29:48 time: 0.2556 data_time: 0.0122 memory: 13708 grad_norm: 4.4247 loss: 2.2664 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.2664 2023/02/18 00:27:43 - mmengine - INFO - Epoch(train) [14][ 120/1320] lr: 2.0000e-02 eta: 3:29:43 time: 0.2550 data_time: 0.0100 memory: 13708 grad_norm: 4.3770 loss: 2.2715 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.2715 2023/02/18 00:27:48 - mmengine - INFO - Epoch(train) [14][ 140/1320] lr: 2.0000e-02 eta: 3:29:37 time: 0.2550 data_time: 0.0104 memory: 13708 grad_norm: 4.3851 loss: 2.2194 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.2194 2023/02/18 00:27:54 - mmengine - INFO - Epoch(train) [14][ 160/1320] lr: 2.0000e-02 eta: 3:29:32 time: 0.2550 data_time: 0.0110 memory: 13708 grad_norm: 4.4198 loss: 2.0612 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.0612 2023/02/18 00:27:59 - mmengine - INFO - Epoch(train) [14][ 180/1320] lr: 2.0000e-02 eta: 3:29:26 time: 0.2542 data_time: 0.0102 memory: 13708 grad_norm: 4.5384 loss: 2.0579 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0579 2023/02/18 00:28:04 - mmengine - INFO - Epoch(train) [14][ 200/1320] lr: 2.0000e-02 eta: 3:29:21 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.4381 loss: 2.1399 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.1399 2023/02/18 00:28:09 - mmengine - INFO - Epoch(train) [14][ 220/1320] lr: 2.0000e-02 eta: 3:29:16 time: 0.2546 data_time: 0.0108 memory: 13708 grad_norm: 4.4011 loss: 1.9464 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.9464 2023/02/18 00:28:14 - mmengine - INFO - Epoch(train) [14][ 240/1320] lr: 2.0000e-02 eta: 3:29:10 time: 0.2568 data_time: 0.0116 memory: 13708 grad_norm: 4.3475 loss: 1.9659 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9659 2023/02/18 00:28:19 - mmengine - INFO - Epoch(train) [14][ 260/1320] lr: 2.0000e-02 eta: 3:29:05 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.3531 loss: 2.0549 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0549 2023/02/18 00:28:24 - mmengine - INFO - Epoch(train) [14][ 280/1320] lr: 2.0000e-02 eta: 3:29:00 time: 0.2549 data_time: 0.0108 memory: 13708 grad_norm: 4.4406 loss: 2.0649 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0649 2023/02/18 00:28:29 - mmengine - INFO - Epoch(train) [14][ 300/1320] lr: 2.0000e-02 eta: 3:28:54 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.4628 loss: 2.0663 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0663 2023/02/18 00:28:34 - mmengine - INFO - Epoch(train) [14][ 320/1320] lr: 2.0000e-02 eta: 3:28:49 time: 0.2548 data_time: 0.0104 memory: 13708 grad_norm: 4.4420 loss: 2.1070 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.1070 2023/02/18 00:28:39 - mmengine - INFO - Epoch(train) [14][ 340/1320] lr: 2.0000e-02 eta: 3:28:44 time: 0.2543 data_time: 0.0103 memory: 13708 grad_norm: 4.4042 loss: 2.0528 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.0528 2023/02/18 00:28:45 - mmengine - INFO - Epoch(train) [14][ 360/1320] lr: 2.0000e-02 eta: 3:28:38 time: 0.2546 data_time: 0.0107 memory: 13708 grad_norm: 4.4498 loss: 2.1561 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1561 2023/02/18 00:28:50 - mmengine - INFO - Epoch(train) [14][ 380/1320] lr: 2.0000e-02 eta: 3:28:33 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 4.3422 loss: 1.9954 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 1.9954 2023/02/18 00:28:55 - mmengine - INFO - Epoch(train) [14][ 400/1320] lr: 2.0000e-02 eta: 3:28:28 time: 0.2544 data_time: 0.0102 memory: 13708 grad_norm: 4.5572 loss: 2.1650 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.1650 2023/02/18 00:29:00 - mmengine - INFO - Epoch(train) [14][ 420/1320] lr: 2.0000e-02 eta: 3:28:22 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.3396 loss: 2.2670 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.2670 2023/02/18 00:29:05 - mmengine - INFO - Epoch(train) [14][ 440/1320] lr: 2.0000e-02 eta: 3:28:17 time: 0.2545 data_time: 0.0102 memory: 13708 grad_norm: 4.4066 loss: 2.1613 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.1613 2023/02/18 00:29:10 - mmengine - INFO - Epoch(train) [14][ 460/1320] lr: 2.0000e-02 eta: 3:28:12 time: 0.2570 data_time: 0.0120 memory: 13708 grad_norm: 4.3291 loss: 2.0694 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0694 2023/02/18 00:29:15 - mmengine - INFO - Epoch(train) [14][ 480/1320] lr: 2.0000e-02 eta: 3:28:06 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 4.3929 loss: 2.1518 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1518 2023/02/18 00:29:20 - mmengine - INFO - Epoch(train) [14][ 500/1320] lr: 2.0000e-02 eta: 3:28:01 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.2977 loss: 1.8906 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8906 2023/02/18 00:29:25 - mmengine - INFO - Epoch(train) [14][ 520/1320] lr: 2.0000e-02 eta: 3:27:56 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.3064 loss: 2.0949 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0949 2023/02/18 00:29:31 - mmengine - INFO - Epoch(train) [14][ 540/1320] lr: 2.0000e-02 eta: 3:27:50 time: 0.2547 data_time: 0.0105 memory: 13708 grad_norm: 4.3682 loss: 2.0863 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0863 2023/02/18 00:29:36 - mmengine - INFO - Epoch(train) [14][ 560/1320] lr: 2.0000e-02 eta: 3:27:45 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.2790 loss: 2.0678 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0678 2023/02/18 00:29:41 - mmengine - INFO - Epoch(train) [14][ 580/1320] lr: 2.0000e-02 eta: 3:27:40 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 4.3507 loss: 1.9708 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.9708 2023/02/18 00:29:46 - mmengine - INFO - Epoch(train) [14][ 600/1320] lr: 2.0000e-02 eta: 3:27:34 time: 0.2561 data_time: 0.0120 memory: 13708 grad_norm: 4.2520 loss: 1.9521 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9521 2023/02/18 00:29:51 - mmengine - INFO - Epoch(train) [14][ 620/1320] lr: 2.0000e-02 eta: 3:27:29 time: 0.2547 data_time: 0.0108 memory: 13708 grad_norm: 4.3671 loss: 2.1636 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1636 2023/02/18 00:29:56 - mmengine - INFO - Epoch(train) [14][ 640/1320] lr: 2.0000e-02 eta: 3:27:24 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.3392 loss: 2.0953 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 2.0953 2023/02/18 00:30:01 - mmengine - INFO - Epoch(train) [14][ 660/1320] lr: 2.0000e-02 eta: 3:27:18 time: 0.2548 data_time: 0.0102 memory: 13708 grad_norm: 4.4529 loss: 1.9966 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9966 2023/02/18 00:30:06 - mmengine - INFO - Epoch(train) [14][ 680/1320] lr: 2.0000e-02 eta: 3:27:13 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.3927 loss: 1.9223 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.9223 2023/02/18 00:30:11 - mmengine - INFO - Epoch(train) [14][ 700/1320] lr: 2.0000e-02 eta: 3:27:08 time: 0.2540 data_time: 0.0101 memory: 13708 grad_norm: 4.3858 loss: 2.2016 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.2016 2023/02/18 00:30:16 - mmengine - INFO - Epoch(train) [14][ 720/1320] lr: 2.0000e-02 eta: 3:27:02 time: 0.2553 data_time: 0.0112 memory: 13708 grad_norm: 4.3861 loss: 2.0619 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0619 2023/02/18 00:30:22 - mmengine - INFO - Epoch(train) [14][ 740/1320] lr: 2.0000e-02 eta: 3:26:57 time: 0.2546 data_time: 0.0104 memory: 13708 grad_norm: 4.3229 loss: 2.2490 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.2490 2023/02/18 00:30:27 - mmengine - INFO - Epoch(train) [14][ 760/1320] lr: 2.0000e-02 eta: 3:26:52 time: 0.2560 data_time: 0.0101 memory: 13708 grad_norm: 4.4496 loss: 1.9286 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9286 2023/02/18 00:30:32 - mmengine - INFO - Epoch(train) [14][ 780/1320] lr: 2.0000e-02 eta: 3:26:46 time: 0.2552 data_time: 0.0105 memory: 13708 grad_norm: 4.5975 loss: 2.1894 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1894 2023/02/18 00:30:37 - mmengine - INFO - Epoch(train) [14][ 800/1320] lr: 2.0000e-02 eta: 3:26:41 time: 0.2550 data_time: 0.0104 memory: 13708 grad_norm: 4.3774 loss: 2.0675 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0675 2023/02/18 00:30:42 - mmengine - INFO - Epoch(train) [14][ 820/1320] lr: 2.0000e-02 eta: 3:26:36 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.5044 loss: 1.9925 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.9925 2023/02/18 00:30:47 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:30:47 - mmengine - INFO - Epoch(train) [14][ 840/1320] lr: 2.0000e-02 eta: 3:26:30 time: 0.2568 data_time: 0.0117 memory: 13708 grad_norm: 4.4411 loss: 2.0238 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.0238 2023/02/18 00:30:52 - mmengine - INFO - Epoch(train) [14][ 860/1320] lr: 2.0000e-02 eta: 3:26:25 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 4.3736 loss: 2.1698 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1698 2023/02/18 00:30:57 - mmengine - INFO - Epoch(train) [14][ 880/1320] lr: 2.0000e-02 eta: 3:26:20 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 4.3070 loss: 2.0158 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0158 2023/02/18 00:31:02 - mmengine - INFO - Epoch(train) [14][ 900/1320] lr: 2.0000e-02 eta: 3:26:14 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.3429 loss: 1.9172 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9172 2023/02/18 00:31:08 - mmengine - INFO - Epoch(train) [14][ 920/1320] lr: 2.0000e-02 eta: 3:26:09 time: 0.2548 data_time: 0.0104 memory: 13708 grad_norm: 4.3835 loss: 2.0871 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0871 2023/02/18 00:31:13 - mmengine - INFO - Epoch(train) [14][ 940/1320] lr: 2.0000e-02 eta: 3:26:04 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 4.3331 loss: 2.0877 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0877 2023/02/18 00:31:18 - mmengine - INFO - Epoch(train) [14][ 960/1320] lr: 2.0000e-02 eta: 3:25:59 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.3420 loss: 2.0744 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0744 2023/02/18 00:31:23 - mmengine - INFO - Epoch(train) [14][ 980/1320] lr: 2.0000e-02 eta: 3:25:53 time: 0.2548 data_time: 0.0101 memory: 13708 grad_norm: 4.3024 loss: 2.1907 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1907 2023/02/18 00:31:28 - mmengine - INFO - Epoch(train) [14][1000/1320] lr: 2.0000e-02 eta: 3:25:48 time: 0.2554 data_time: 0.0116 memory: 13708 grad_norm: 4.3987 loss: 2.0074 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0074 2023/02/18 00:31:33 - mmengine - INFO - Epoch(train) [14][1020/1320] lr: 2.0000e-02 eta: 3:25:43 time: 0.2556 data_time: 0.0111 memory: 13708 grad_norm: 4.4433 loss: 2.2041 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.2041 2023/02/18 00:31:38 - mmengine - INFO - Epoch(train) [14][1040/1320] lr: 2.0000e-02 eta: 3:25:37 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.2782 loss: 2.1516 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1516 2023/02/18 00:31:43 - mmengine - INFO - Epoch(train) [14][1060/1320] lr: 2.0000e-02 eta: 3:25:32 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.5281 loss: 2.0934 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0934 2023/02/18 00:31:48 - mmengine - INFO - Epoch(train) [14][1080/1320] lr: 2.0000e-02 eta: 3:25:27 time: 0.2551 data_time: 0.0102 memory: 13708 grad_norm: 4.3836 loss: 1.9785 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.9785 2023/02/18 00:31:53 - mmengine - INFO - Epoch(train) [14][1100/1320] lr: 2.0000e-02 eta: 3:25:21 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.3462 loss: 2.0353 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0353 2023/02/18 00:31:59 - mmengine - INFO - Epoch(train) [14][1120/1320] lr: 2.0000e-02 eta: 3:25:16 time: 0.2576 data_time: 0.0134 memory: 13708 grad_norm: 4.4374 loss: 1.8492 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.8492 2023/02/18 00:32:04 - mmengine - INFO - Epoch(train) [14][1140/1320] lr: 2.0000e-02 eta: 3:25:11 time: 0.2542 data_time: 0.0103 memory: 13708 grad_norm: 4.2295 loss: 2.0005 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0005 2023/02/18 00:32:09 - mmengine - INFO - Epoch(train) [14][1160/1320] lr: 2.0000e-02 eta: 3:25:05 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.3185 loss: 1.8806 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8806 2023/02/18 00:32:14 - mmengine - INFO - Epoch(train) [14][1180/1320] lr: 2.0000e-02 eta: 3:25:00 time: 0.2572 data_time: 0.0125 memory: 13708 grad_norm: 4.4473 loss: 1.9904 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9904 2023/02/18 00:32:19 - mmengine - INFO - Epoch(train) [14][1200/1320] lr: 2.0000e-02 eta: 3:24:55 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.2831 loss: 1.9362 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.9362 2023/02/18 00:32:24 - mmengine - INFO - Epoch(train) [14][1220/1320] lr: 2.0000e-02 eta: 3:24:50 time: 0.2548 data_time: 0.0104 memory: 13708 grad_norm: 4.4737 loss: 2.2078 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2078 2023/02/18 00:32:29 - mmengine - INFO - Epoch(train) [14][1240/1320] lr: 2.0000e-02 eta: 3:24:44 time: 0.2548 data_time: 0.0102 memory: 13708 grad_norm: 4.3198 loss: 2.2274 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.2274 2023/02/18 00:32:34 - mmengine - INFO - Epoch(train) [14][1260/1320] lr: 2.0000e-02 eta: 3:24:39 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 4.2721 loss: 2.1703 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.1703 2023/02/18 00:32:39 - mmengine - INFO - Epoch(train) [14][1280/1320] lr: 2.0000e-02 eta: 3:24:34 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.3839 loss: 2.2709 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.2709 2023/02/18 00:32:45 - mmengine - INFO - Epoch(train) [14][1300/1320] lr: 2.0000e-02 eta: 3:24:28 time: 0.2544 data_time: 0.0101 memory: 13708 grad_norm: 4.2873 loss: 2.1185 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1185 2023/02/18 00:32:50 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:32:50 - mmengine - INFO - Epoch(train) [14][1320/1320] lr: 2.0000e-02 eta: 3:24:23 time: 0.2504 data_time: 0.0102 memory: 13708 grad_norm: 4.3318 loss: 2.2224 top1_acc: 0.5455 top5_acc: 0.7273 loss_cls: 2.2224 2023/02/18 00:32:52 - mmengine - INFO - Epoch(val) [14][ 20/194] eta: 0:00:21 time: 0.1253 data_time: 0.0575 memory: 1818 2023/02/18 00:32:54 - mmengine - INFO - Epoch(val) [14][ 40/194] eta: 0:00:16 time: 0.0870 data_time: 0.0195 memory: 1818 2023/02/18 00:32:56 - mmengine - INFO - Epoch(val) [14][ 60/194] eta: 0:00:13 time: 0.0884 data_time: 0.0213 memory: 1818 2023/02/18 00:32:57 - mmengine - INFO - Epoch(val) [14][ 80/194] eta: 0:00:11 time: 0.0950 data_time: 0.0169 memory: 1818 2023/02/18 00:32:59 - mmengine - INFO - Epoch(val) [14][100/194] eta: 0:00:09 time: 0.0838 data_time: 0.0158 memory: 1818 2023/02/18 00:33:01 - mmengine - INFO - Epoch(val) [14][120/194] eta: 0:00:06 time: 0.0852 data_time: 0.0171 memory: 1818 2023/02/18 00:33:03 - mmengine - INFO - Epoch(val) [14][140/194] eta: 0:00:05 time: 0.0895 data_time: 0.0221 memory: 1818 2023/02/18 00:33:04 - mmengine - INFO - Epoch(val) [14][160/194] eta: 0:00:03 time: 0.0805 data_time: 0.0131 memory: 1818 2023/02/18 00:33:06 - mmengine - INFO - Epoch(val) [14][180/194] eta: 0:00:01 time: 0.0860 data_time: 0.0183 memory: 1818 2023/02/18 00:33:08 - mmengine - INFO - Epoch(val) [14][194/194] acc/top1: 0.4520 acc/top5: 0.7450 acc/mean1: 0.3858 2023/02/18 00:33:08 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_13.pth is removed 2023/02/18 00:33:09 - mmengine - INFO - The best checkpoint with 0.4520 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2023/02/18 00:33:15 - mmengine - INFO - Epoch(train) [15][ 20/1320] lr: 2.0000e-02 eta: 3:24:20 time: 0.2968 data_time: 0.0407 memory: 13708 grad_norm: 4.3519 loss: 2.2091 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.2091 2023/02/18 00:33:20 - mmengine - INFO - Epoch(train) [15][ 40/1320] lr: 2.0000e-02 eta: 3:24:14 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.3504 loss: 1.8859 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8859 2023/02/18 00:33:25 - mmengine - INFO - Epoch(train) [15][ 60/1320] lr: 2.0000e-02 eta: 3:24:09 time: 0.2548 data_time: 0.0110 memory: 13708 grad_norm: 4.4469 loss: 2.0565 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0565 2023/02/18 00:33:30 - mmengine - INFO - Epoch(train) [15][ 80/1320] lr: 2.0000e-02 eta: 3:24:04 time: 0.2547 data_time: 0.0103 memory: 13708 grad_norm: 4.4007 loss: 2.1169 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1169 2023/02/18 00:33:35 - mmengine - INFO - Epoch(train) [15][ 100/1320] lr: 2.0000e-02 eta: 3:23:58 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 4.3581 loss: 2.1899 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.1899 2023/02/18 00:33:40 - mmengine - INFO - Epoch(train) [15][ 120/1320] lr: 2.0000e-02 eta: 3:23:53 time: 0.2554 data_time: 0.0112 memory: 13708 grad_norm: 4.4082 loss: 2.0991 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0991 2023/02/18 00:33:46 - mmengine - INFO - Epoch(train) [15][ 140/1320] lr: 2.0000e-02 eta: 3:23:48 time: 0.2543 data_time: 0.0103 memory: 13708 grad_norm: 4.4610 loss: 2.2343 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.2343 2023/02/18 00:33:51 - mmengine - INFO - Epoch(train) [15][ 160/1320] lr: 2.0000e-02 eta: 3:23:42 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.3646 loss: 2.1800 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1800 2023/02/18 00:33:56 - mmengine - INFO - Epoch(train) [15][ 180/1320] lr: 2.0000e-02 eta: 3:23:37 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 4.4947 loss: 1.8059 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.8059 2023/02/18 00:34:01 - mmengine - INFO - Epoch(train) [15][ 200/1320] lr: 2.0000e-02 eta: 3:23:32 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 4.5619 loss: 2.0207 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0207 2023/02/18 00:34:06 - mmengine - INFO - Epoch(train) [15][ 220/1320] lr: 2.0000e-02 eta: 3:23:26 time: 0.2541 data_time: 0.0104 memory: 13708 grad_norm: 4.3390 loss: 2.1154 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 2.1154 2023/02/18 00:34:11 - mmengine - INFO - Epoch(train) [15][ 240/1320] lr: 2.0000e-02 eta: 3:23:21 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 4.5498 loss: 2.1721 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1721 2023/02/18 00:34:16 - mmengine - INFO - Epoch(train) [15][ 260/1320] lr: 2.0000e-02 eta: 3:23:16 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 4.4759 loss: 2.0462 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0462 2023/02/18 00:34:21 - mmengine - INFO - Epoch(train) [15][ 280/1320] lr: 2.0000e-02 eta: 3:23:10 time: 0.2549 data_time: 0.0102 memory: 13708 grad_norm: 4.3840 loss: 2.0768 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0768 2023/02/18 00:34:26 - mmengine - INFO - Epoch(train) [15][ 300/1320] lr: 2.0000e-02 eta: 3:23:05 time: 0.2549 data_time: 0.0103 memory: 13708 grad_norm: 4.3326 loss: 2.0278 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.0278 2023/02/18 00:34:31 - mmengine - INFO - Epoch(train) [15][ 320/1320] lr: 2.0000e-02 eta: 3:23:00 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 4.3963 loss: 2.0096 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.0096 2023/02/18 00:34:37 - mmengine - INFO - Epoch(train) [15][ 340/1320] lr: 2.0000e-02 eta: 3:22:55 time: 0.2552 data_time: 0.0105 memory: 13708 grad_norm: 4.4311 loss: 1.8883 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8883 2023/02/18 00:34:42 - mmengine - INFO - Epoch(train) [15][ 360/1320] lr: 2.0000e-02 eta: 3:22:49 time: 0.2558 data_time: 0.0105 memory: 13708 grad_norm: 4.3118 loss: 2.0378 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0378 2023/02/18 00:34:47 - mmengine - INFO - Epoch(train) [15][ 380/1320] lr: 2.0000e-02 eta: 3:22:44 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 4.4487 loss: 2.1149 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1149 2023/02/18 00:34:52 - mmengine - INFO - Epoch(train) [15][ 400/1320] lr: 2.0000e-02 eta: 3:22:39 time: 0.2545 data_time: 0.0102 memory: 13708 grad_norm: 4.4841 loss: 2.0870 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0870 2023/02/18 00:34:57 - mmengine - INFO - Epoch(train) [15][ 420/1320] lr: 2.0000e-02 eta: 3:22:33 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.3896 loss: 2.0564 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0564 2023/02/18 00:35:02 - mmengine - INFO - Epoch(train) [15][ 440/1320] lr: 2.0000e-02 eta: 3:22:28 time: 0.2545 data_time: 0.0104 memory: 13708 grad_norm: 4.4145 loss: 2.0896 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0896 2023/02/18 00:35:07 - mmengine - INFO - Epoch(train) [15][ 460/1320] lr: 2.0000e-02 eta: 3:22:23 time: 0.2549 data_time: 0.0103 memory: 13708 grad_norm: 4.4522 loss: 1.9608 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 1.9608 2023/02/18 00:35:12 - mmengine - INFO - Epoch(train) [15][ 480/1320] lr: 2.0000e-02 eta: 3:22:17 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.3346 loss: 2.0238 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.0238 2023/02/18 00:35:17 - mmengine - INFO - Epoch(train) [15][ 500/1320] lr: 2.0000e-02 eta: 3:22:12 time: 0.2562 data_time: 0.0120 memory: 13708 grad_norm: 4.3394 loss: 1.9623 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9623 2023/02/18 00:35:23 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:35:23 - mmengine - INFO - Epoch(train) [15][ 520/1320] lr: 2.0000e-02 eta: 3:22:07 time: 0.2552 data_time: 0.0105 memory: 13708 grad_norm: 4.4708 loss: 1.9859 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9859 2023/02/18 00:35:28 - mmengine - INFO - Epoch(train) [15][ 540/1320] lr: 2.0000e-02 eta: 3:22:02 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 4.3595 loss: 2.0737 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 2.0737 2023/02/18 00:35:33 - mmengine - INFO - Epoch(train) [15][ 560/1320] lr: 2.0000e-02 eta: 3:21:56 time: 0.2542 data_time: 0.0102 memory: 13708 grad_norm: 4.4231 loss: 2.0849 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0849 2023/02/18 00:35:38 - mmengine - INFO - Epoch(train) [15][ 580/1320] lr: 2.0000e-02 eta: 3:21:51 time: 0.2550 data_time: 0.0109 memory: 13708 grad_norm: 4.3924 loss: 2.1010 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 2.1010 2023/02/18 00:35:43 - mmengine - INFO - Epoch(train) [15][ 600/1320] lr: 2.0000e-02 eta: 3:21:46 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.6150 loss: 2.1890 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1890 2023/02/18 00:35:48 - mmengine - INFO - Epoch(train) [15][ 620/1320] lr: 2.0000e-02 eta: 3:21:40 time: 0.2589 data_time: 0.0145 memory: 13708 grad_norm: 4.5532 loss: 2.0973 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.0973 2023/02/18 00:35:53 - mmengine - INFO - Epoch(train) [15][ 640/1320] lr: 2.0000e-02 eta: 3:21:35 time: 0.2547 data_time: 0.0109 memory: 13708 grad_norm: 4.2733 loss: 1.9054 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 1.9054 2023/02/18 00:35:58 - mmengine - INFO - Epoch(train) [15][ 660/1320] lr: 2.0000e-02 eta: 3:21:30 time: 0.2555 data_time: 0.0114 memory: 13708 grad_norm: 4.4590 loss: 2.2046 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.2046 2023/02/18 00:36:03 - mmengine - INFO - Epoch(train) [15][ 680/1320] lr: 2.0000e-02 eta: 3:21:25 time: 0.2563 data_time: 0.0119 memory: 13708 grad_norm: 4.4007 loss: 1.9805 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 1.9805 2023/02/18 00:36:09 - mmengine - INFO - Epoch(train) [15][ 700/1320] lr: 2.0000e-02 eta: 3:21:19 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.4071 loss: 2.0971 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0971 2023/02/18 00:36:14 - mmengine - INFO - Epoch(train) [15][ 720/1320] lr: 2.0000e-02 eta: 3:21:14 time: 0.2542 data_time: 0.0101 memory: 13708 grad_norm: 4.3124 loss: 1.9816 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9816 2023/02/18 00:36:19 - mmengine - INFO - Epoch(train) [15][ 740/1320] lr: 2.0000e-02 eta: 3:21:09 time: 0.2546 data_time: 0.0101 memory: 13708 grad_norm: 4.3584 loss: 2.0666 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.0666 2023/02/18 00:36:24 - mmengine - INFO - Epoch(train) [15][ 760/1320] lr: 2.0000e-02 eta: 3:21:03 time: 0.2547 data_time: 0.0110 memory: 13708 grad_norm: 4.3573 loss: 2.1614 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.1614 2023/02/18 00:36:29 - mmengine - INFO - Epoch(train) [15][ 780/1320] lr: 2.0000e-02 eta: 3:20:58 time: 0.2561 data_time: 0.0115 memory: 13708 grad_norm: 4.3996 loss: 1.9639 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9639 2023/02/18 00:36:34 - mmengine - INFO - Epoch(train) [15][ 800/1320] lr: 2.0000e-02 eta: 3:20:53 time: 0.2559 data_time: 0.0117 memory: 13708 grad_norm: 4.4768 loss: 2.1177 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1177 2023/02/18 00:36:39 - mmengine - INFO - Epoch(train) [15][ 820/1320] lr: 2.0000e-02 eta: 3:20:47 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.3399 loss: 2.1930 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1930 2023/02/18 00:36:44 - mmengine - INFO - Epoch(train) [15][ 840/1320] lr: 2.0000e-02 eta: 3:20:42 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 4.2836 loss: 1.8713 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.8713 2023/02/18 00:36:49 - mmengine - INFO - Epoch(train) [15][ 860/1320] lr: 2.0000e-02 eta: 3:20:37 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.3681 loss: 1.8803 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8803 2023/02/18 00:36:54 - mmengine - INFO - Epoch(train) [15][ 880/1320] lr: 2.0000e-02 eta: 3:20:32 time: 0.2558 data_time: 0.0112 memory: 13708 grad_norm: 4.4243 loss: 2.1657 top1_acc: 0.5625 top5_acc: 0.5625 loss_cls: 2.1657 2023/02/18 00:37:00 - mmengine - INFO - Epoch(train) [15][ 900/1320] lr: 2.0000e-02 eta: 3:20:26 time: 0.2552 data_time: 0.0104 memory: 13708 grad_norm: 4.3906 loss: 2.1094 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1094 2023/02/18 00:37:05 - mmengine - INFO - Epoch(train) [15][ 920/1320] lr: 2.0000e-02 eta: 3:20:21 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.4639 loss: 1.9303 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 1.9303 2023/02/18 00:37:10 - mmengine - INFO - Epoch(train) [15][ 940/1320] lr: 2.0000e-02 eta: 3:20:16 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.5258 loss: 2.1828 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.1828 2023/02/18 00:37:15 - mmengine - INFO - Epoch(train) [15][ 960/1320] lr: 2.0000e-02 eta: 3:20:10 time: 0.2554 data_time: 0.0101 memory: 13708 grad_norm: 4.4263 loss: 2.0759 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0759 2023/02/18 00:37:20 - mmengine - INFO - Epoch(train) [15][ 980/1320] lr: 2.0000e-02 eta: 3:20:05 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.4005 loss: 2.0867 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0867 2023/02/18 00:37:25 - mmengine - INFO - Epoch(train) [15][1000/1320] lr: 2.0000e-02 eta: 3:20:00 time: 0.2545 data_time: 0.0102 memory: 13708 grad_norm: 4.3943 loss: 2.0858 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.0858 2023/02/18 00:37:30 - mmengine - INFO - Epoch(train) [15][1020/1320] lr: 2.0000e-02 eta: 3:19:55 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.3372 loss: 1.8324 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.8324 2023/02/18 00:37:35 - mmengine - INFO - Epoch(train) [15][1040/1320] lr: 2.0000e-02 eta: 3:19:49 time: 0.2545 data_time: 0.0102 memory: 13708 grad_norm: 4.3440 loss: 2.2062 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.2062 2023/02/18 00:37:40 - mmengine - INFO - Epoch(train) [15][1060/1320] lr: 2.0000e-02 eta: 3:19:44 time: 0.2569 data_time: 0.0116 memory: 13708 grad_norm: 4.3430 loss: 1.8035 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.8035 2023/02/18 00:37:46 - mmengine - INFO - Epoch(train) [15][1080/1320] lr: 2.0000e-02 eta: 3:19:39 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.4838 loss: 2.1617 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.1617 2023/02/18 00:37:51 - mmengine - INFO - Epoch(train) [15][1100/1320] lr: 2.0000e-02 eta: 3:19:33 time: 0.2545 data_time: 0.0102 memory: 13708 grad_norm: 4.4215 loss: 2.1686 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1686 2023/02/18 00:37:56 - mmengine - INFO - Epoch(train) [15][1120/1320] lr: 2.0000e-02 eta: 3:19:28 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.3215 loss: 2.0173 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.0173 2023/02/18 00:38:01 - mmengine - INFO - Epoch(train) [15][1140/1320] lr: 2.0000e-02 eta: 3:19:23 time: 0.2546 data_time: 0.0101 memory: 13708 grad_norm: 4.4201 loss: 2.0459 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0459 2023/02/18 00:38:06 - mmengine - INFO - Epoch(train) [15][1160/1320] lr: 2.0000e-02 eta: 3:19:18 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 4.3475 loss: 2.2758 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.2758 2023/02/18 00:38:11 - mmengine - INFO - Epoch(train) [15][1180/1320] lr: 2.0000e-02 eta: 3:19:12 time: 0.2548 data_time: 0.0104 memory: 13708 grad_norm: 4.4106 loss: 2.2087 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.2087 2023/02/18 00:38:16 - mmengine - INFO - Epoch(train) [15][1200/1320] lr: 2.0000e-02 eta: 3:19:07 time: 0.2552 data_time: 0.0102 memory: 13708 grad_norm: 4.3498 loss: 1.9080 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9080 2023/02/18 00:38:21 - mmengine - INFO - Epoch(train) [15][1220/1320] lr: 2.0000e-02 eta: 3:19:02 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 4.3083 loss: 1.9119 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9119 2023/02/18 00:38:26 - mmengine - INFO - Epoch(train) [15][1240/1320] lr: 2.0000e-02 eta: 3:18:56 time: 0.2546 data_time: 0.0107 memory: 13708 grad_norm: 4.3761 loss: 2.2087 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.2087 2023/02/18 00:38:31 - mmengine - INFO - Epoch(train) [15][1260/1320] lr: 2.0000e-02 eta: 3:18:51 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.3133 loss: 2.0412 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 2.0412 2023/02/18 00:38:37 - mmengine - INFO - Epoch(train) [15][1280/1320] lr: 2.0000e-02 eta: 3:18:46 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.3788 loss: 2.1667 top1_acc: 0.3750 top5_acc: 0.9375 loss_cls: 2.1667 2023/02/18 00:38:42 - mmengine - INFO - Epoch(train) [15][1300/1320] lr: 2.0000e-02 eta: 3:18:40 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.4210 loss: 2.1626 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.1626 2023/02/18 00:38:47 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:38:47 - mmengine - INFO - Epoch(train) [15][1320/1320] lr: 2.0000e-02 eta: 3:18:35 time: 0.2503 data_time: 0.0100 memory: 13708 grad_norm: 4.4280 loss: 2.1808 top1_acc: 0.4545 top5_acc: 0.5455 loss_cls: 2.1808 2023/02/18 00:38:47 - mmengine - INFO - Saving checkpoint at 15 epochs 2023/02/18 00:38:50 - mmengine - INFO - Epoch(val) [15][ 20/194] eta: 0:00:22 time: 0.1293 data_time: 0.0607 memory: 1818 2023/02/18 00:38:52 - mmengine - INFO - Epoch(val) [15][ 40/194] eta: 0:00:16 time: 0.0878 data_time: 0.0201 memory: 1818 2023/02/18 00:38:54 - mmengine - INFO - Epoch(val) [15][ 60/194] eta: 0:00:13 time: 0.0876 data_time: 0.0199 memory: 1818 2023/02/18 00:38:56 - mmengine - INFO - Epoch(val) [15][ 80/194] eta: 0:00:11 time: 0.0828 data_time: 0.0149 memory: 1818 2023/02/18 00:38:57 - mmengine - INFO - Epoch(val) [15][100/194] eta: 0:00:08 time: 0.0897 data_time: 0.0226 memory: 1818 2023/02/18 00:38:59 - mmengine - INFO - Epoch(val) [15][120/194] eta: 0:00:06 time: 0.0842 data_time: 0.0167 memory: 1818 2023/02/18 00:39:01 - mmengine - INFO - Epoch(val) [15][140/194] eta: 0:00:05 time: 0.0939 data_time: 0.0258 memory: 1818 2023/02/18 00:39:03 - mmengine - INFO - Epoch(val) [15][160/194] eta: 0:00:03 time: 0.0813 data_time: 0.0135 memory: 1818 2023/02/18 00:39:04 - mmengine - INFO - Epoch(val) [15][180/194] eta: 0:00:01 time: 0.0808 data_time: 0.0152 memory: 1818 2023/02/18 00:39:06 - mmengine - INFO - Epoch(val) [15][194/194] acc/top1: 0.4551 acc/top5: 0.7438 acc/mean1: 0.3778 2023/02/18 00:39:06 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_14.pth is removed 2023/02/18 00:39:07 - mmengine - INFO - The best checkpoint with 0.4551 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2023/02/18 00:39:13 - mmengine - INFO - Epoch(train) [16][ 20/1320] lr: 2.0000e-02 eta: 3:18:31 time: 0.2920 data_time: 0.0395 memory: 13708 grad_norm: 4.1938 loss: 2.0450 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.0450 2023/02/18 00:39:18 - mmengine - INFO - Epoch(train) [16][ 40/1320] lr: 2.0000e-02 eta: 3:18:26 time: 0.2572 data_time: 0.0113 memory: 13708 grad_norm: 4.4285 loss: 2.1191 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1191 2023/02/18 00:39:23 - mmengine - INFO - Epoch(train) [16][ 60/1320] lr: 2.0000e-02 eta: 3:18:21 time: 0.2568 data_time: 0.0118 memory: 13708 grad_norm: 4.5061 loss: 2.1388 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1388 2023/02/18 00:39:28 - mmengine - INFO - Epoch(train) [16][ 80/1320] lr: 2.0000e-02 eta: 3:18:16 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 4.3905 loss: 2.0130 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.0130 2023/02/18 00:39:33 - mmengine - INFO - Epoch(train) [16][ 100/1320] lr: 2.0000e-02 eta: 3:18:10 time: 0.2568 data_time: 0.0122 memory: 13708 grad_norm: 4.2684 loss: 1.9851 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9851 2023/02/18 00:39:38 - mmengine - INFO - Epoch(train) [16][ 120/1320] lr: 2.0000e-02 eta: 3:18:05 time: 0.2565 data_time: 0.0122 memory: 13708 grad_norm: 4.4341 loss: 2.0858 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0858 2023/02/18 00:39:44 - mmengine - INFO - Epoch(train) [16][ 140/1320] lr: 2.0000e-02 eta: 3:18:00 time: 0.2554 data_time: 0.0112 memory: 13708 grad_norm: 4.4543 loss: 1.9743 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9743 2023/02/18 00:39:49 - mmengine - INFO - Epoch(train) [16][ 160/1320] lr: 2.0000e-02 eta: 3:17:55 time: 0.2551 data_time: 0.0103 memory: 13708 grad_norm: 4.4116 loss: 1.9945 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.9945 2023/02/18 00:39:54 - mmengine - INFO - Epoch(train) [16][ 180/1320] lr: 2.0000e-02 eta: 3:17:49 time: 0.2555 data_time: 0.0112 memory: 13708 grad_norm: 4.4543 loss: 1.8984 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8984 2023/02/18 00:39:59 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:39:59 - mmengine - INFO - Epoch(train) [16][ 200/1320] lr: 2.0000e-02 eta: 3:17:44 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.5958 loss: 2.0467 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0467 2023/02/18 00:40:04 - mmengine - INFO - Epoch(train) [16][ 220/1320] lr: 2.0000e-02 eta: 3:17:39 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 4.5474 loss: 2.0083 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0083 2023/02/18 00:40:09 - mmengine - INFO - Epoch(train) [16][ 240/1320] lr: 2.0000e-02 eta: 3:17:34 time: 0.2558 data_time: 0.0106 memory: 13708 grad_norm: 4.3463 loss: 2.2195 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.2195 2023/02/18 00:40:14 - mmengine - INFO - Epoch(train) [16][ 260/1320] lr: 2.0000e-02 eta: 3:17:28 time: 0.2550 data_time: 0.0101 memory: 13708 grad_norm: 4.4848 loss: 2.1368 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.1368 2023/02/18 00:40:19 - mmengine - INFO - Epoch(train) [16][ 280/1320] lr: 2.0000e-02 eta: 3:17:23 time: 0.2558 data_time: 0.0101 memory: 13708 grad_norm: 4.3546 loss: 1.9061 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.9061 2023/02/18 00:40:24 - mmengine - INFO - Epoch(train) [16][ 300/1320] lr: 2.0000e-02 eta: 3:17:18 time: 0.2554 data_time: 0.0102 memory: 13708 grad_norm: 4.4792 loss: 2.0962 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 2.0962 2023/02/18 00:40:30 - mmengine - INFO - Epoch(train) [16][ 320/1320] lr: 2.0000e-02 eta: 3:17:12 time: 0.2543 data_time: 0.0106 memory: 13708 grad_norm: 4.4759 loss: 1.9428 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9428 2023/02/18 00:40:35 - mmengine - INFO - Epoch(train) [16][ 340/1320] lr: 2.0000e-02 eta: 3:17:07 time: 0.2548 data_time: 0.0104 memory: 13708 grad_norm: 4.3555 loss: 2.0561 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0561 2023/02/18 00:40:40 - mmengine - INFO - Epoch(train) [16][ 360/1320] lr: 2.0000e-02 eta: 3:17:02 time: 0.2547 data_time: 0.0103 memory: 13708 grad_norm: 4.4686 loss: 1.9234 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 1.9234 2023/02/18 00:40:45 - mmengine - INFO - Epoch(train) [16][ 380/1320] lr: 2.0000e-02 eta: 3:16:57 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.4674 loss: 2.0604 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0604 2023/02/18 00:40:50 - mmengine - INFO - Epoch(train) [16][ 400/1320] lr: 2.0000e-02 eta: 3:16:51 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.5348 loss: 2.3015 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.3015 2023/02/18 00:40:55 - mmengine - INFO - Epoch(train) [16][ 420/1320] lr: 2.0000e-02 eta: 3:16:46 time: 0.2547 data_time: 0.0103 memory: 13708 grad_norm: 4.5602 loss: 2.1029 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1029 2023/02/18 00:41:00 - mmengine - INFO - Epoch(train) [16][ 440/1320] lr: 2.0000e-02 eta: 3:16:41 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.5701 loss: 2.1597 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1597 2023/02/18 00:41:05 - mmengine - INFO - Epoch(train) [16][ 460/1320] lr: 2.0000e-02 eta: 3:16:35 time: 0.2545 data_time: 0.0103 memory: 13708 grad_norm: 4.5459 loss: 2.1510 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 2.1510 2023/02/18 00:41:10 - mmengine - INFO - Epoch(train) [16][ 480/1320] lr: 2.0000e-02 eta: 3:16:30 time: 0.2551 data_time: 0.0103 memory: 13708 grad_norm: 4.3695 loss: 2.1865 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1865 2023/02/18 00:41:15 - mmengine - INFO - Epoch(train) [16][ 500/1320] lr: 2.0000e-02 eta: 3:16:25 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 4.4508 loss: 2.1459 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1459 2023/02/18 00:41:21 - mmengine - INFO - Epoch(train) [16][ 520/1320] lr: 2.0000e-02 eta: 3:16:20 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.3159 loss: 2.0934 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.0934 2023/02/18 00:41:26 - mmengine - INFO - Epoch(train) [16][ 540/1320] lr: 2.0000e-02 eta: 3:16:14 time: 0.2545 data_time: 0.0101 memory: 13708 grad_norm: 4.4292 loss: 2.1091 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.1091 2023/02/18 00:41:31 - mmengine - INFO - Epoch(train) [16][ 560/1320] lr: 2.0000e-02 eta: 3:16:09 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 4.5554 loss: 2.0049 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.0049 2023/02/18 00:41:36 - mmengine - INFO - Epoch(train) [16][ 580/1320] lr: 2.0000e-02 eta: 3:16:04 time: 0.2544 data_time: 0.0103 memory: 13708 grad_norm: 4.4575 loss: 2.0549 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0549 2023/02/18 00:41:41 - mmengine - INFO - Epoch(train) [16][ 600/1320] lr: 2.0000e-02 eta: 3:15:58 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 4.3196 loss: 1.9906 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9906 2023/02/18 00:41:46 - mmengine - INFO - Epoch(train) [16][ 620/1320] lr: 2.0000e-02 eta: 3:15:53 time: 0.2547 data_time: 0.0105 memory: 13708 grad_norm: 4.3705 loss: 2.0269 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 2.0269 2023/02/18 00:41:51 - mmengine - INFO - Epoch(train) [16][ 640/1320] lr: 2.0000e-02 eta: 3:15:48 time: 0.2553 data_time: 0.0101 memory: 13708 grad_norm: 4.3800 loss: 2.1070 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1070 2023/02/18 00:41:56 - mmengine - INFO - Epoch(train) [16][ 660/1320] lr: 2.0000e-02 eta: 3:15:43 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.3536 loss: 2.0927 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0927 2023/02/18 00:42:01 - mmengine - INFO - Epoch(train) [16][ 680/1320] lr: 2.0000e-02 eta: 3:15:37 time: 0.2543 data_time: 0.0102 memory: 13708 grad_norm: 4.4248 loss: 1.9826 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9826 2023/02/18 00:42:06 - mmengine - INFO - Epoch(train) [16][ 700/1320] lr: 2.0000e-02 eta: 3:15:32 time: 0.2546 data_time: 0.0107 memory: 13708 grad_norm: 4.6343 loss: 2.0155 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0155 2023/02/18 00:42:12 - mmengine - INFO - Epoch(train) [16][ 720/1320] lr: 2.0000e-02 eta: 3:15:27 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.4969 loss: 2.0422 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0422 2023/02/18 00:42:17 - mmengine - INFO - Epoch(train) [16][ 740/1320] lr: 2.0000e-02 eta: 3:15:21 time: 0.2549 data_time: 0.0102 memory: 13708 grad_norm: 4.3601 loss: 2.0794 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0794 2023/02/18 00:42:22 - mmengine - INFO - Epoch(train) [16][ 760/1320] lr: 2.0000e-02 eta: 3:15:16 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.3147 loss: 2.0141 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0141 2023/02/18 00:42:27 - mmengine - INFO - Epoch(train) [16][ 780/1320] lr: 2.0000e-02 eta: 3:15:11 time: 0.2550 data_time: 0.0104 memory: 13708 grad_norm: 4.3520 loss: 1.8946 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8946 2023/02/18 00:42:32 - mmengine - INFO - Epoch(train) [16][ 800/1320] lr: 2.0000e-02 eta: 3:15:06 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.3778 loss: 2.1092 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1092 2023/02/18 00:42:37 - mmengine - INFO - Epoch(train) [16][ 820/1320] lr: 2.0000e-02 eta: 3:15:00 time: 0.2572 data_time: 0.0123 memory: 13708 grad_norm: 4.4510 loss: 2.0791 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0791 2023/02/18 00:42:42 - mmengine - INFO - Epoch(train) [16][ 840/1320] lr: 2.0000e-02 eta: 3:14:55 time: 0.2544 data_time: 0.0105 memory: 13708 grad_norm: 4.5205 loss: 2.0621 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0621 2023/02/18 00:42:47 - mmengine - INFO - Epoch(train) [16][ 860/1320] lr: 2.0000e-02 eta: 3:14:50 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.3498 loss: 2.0094 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0094 2023/02/18 00:42:52 - mmengine - INFO - Epoch(train) [16][ 880/1320] lr: 2.0000e-02 eta: 3:14:44 time: 0.2555 data_time: 0.0112 memory: 13708 grad_norm: 4.3957 loss: 2.0692 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.0692 2023/02/18 00:42:57 - mmengine - INFO - Epoch(train) [16][ 900/1320] lr: 2.0000e-02 eta: 3:14:39 time: 0.2552 data_time: 0.0103 memory: 13708 grad_norm: 4.4538 loss: 1.9915 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9915 2023/02/18 00:43:03 - mmengine - INFO - Epoch(train) [16][ 920/1320] lr: 2.0000e-02 eta: 3:14:34 time: 0.2546 data_time: 0.0107 memory: 13708 grad_norm: 4.3796 loss: 2.1160 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.1160 2023/02/18 00:43:08 - mmengine - INFO - Epoch(train) [16][ 940/1320] lr: 2.0000e-02 eta: 3:14:29 time: 0.2561 data_time: 0.0121 memory: 13708 grad_norm: 4.3490 loss: 2.1425 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.1425 2023/02/18 00:43:13 - mmengine - INFO - Epoch(train) [16][ 960/1320] lr: 2.0000e-02 eta: 3:14:23 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.2056 loss: 2.1686 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1686 2023/02/18 00:43:18 - mmengine - INFO - Epoch(train) [16][ 980/1320] lr: 2.0000e-02 eta: 3:14:18 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 4.2824 loss: 1.9226 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9226 2023/02/18 00:43:23 - mmengine - INFO - Epoch(train) [16][1000/1320] lr: 2.0000e-02 eta: 3:14:13 time: 0.2567 data_time: 0.0122 memory: 13708 grad_norm: 4.5727 loss: 1.9808 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9808 2023/02/18 00:43:28 - mmengine - INFO - Epoch(train) [16][1020/1320] lr: 2.0000e-02 eta: 3:14:08 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.4359 loss: 1.9936 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 1.9936 2023/02/18 00:43:33 - mmengine - INFO - Epoch(train) [16][1040/1320] lr: 2.0000e-02 eta: 3:14:02 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.4511 loss: 2.0110 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0110 2023/02/18 00:43:38 - mmengine - INFO - Epoch(train) [16][1060/1320] lr: 2.0000e-02 eta: 3:13:57 time: 0.2546 data_time: 0.0104 memory: 13708 grad_norm: 4.4246 loss: 1.9765 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9765 2023/02/18 00:43:43 - mmengine - INFO - Epoch(train) [16][1080/1320] lr: 2.0000e-02 eta: 3:13:52 time: 0.2553 data_time: 0.0105 memory: 13708 grad_norm: 4.3998 loss: 1.9904 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9904 2023/02/18 00:43:49 - mmengine - INFO - Epoch(train) [16][1100/1320] lr: 2.0000e-02 eta: 3:13:47 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.2514 loss: 2.1164 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.1164 2023/02/18 00:43:54 - mmengine - INFO - Epoch(train) [16][1120/1320] lr: 2.0000e-02 eta: 3:13:41 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.4732 loss: 2.1235 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.1235 2023/02/18 00:43:59 - mmengine - INFO - Epoch(train) [16][1140/1320] lr: 2.0000e-02 eta: 3:13:36 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.3233 loss: 2.1946 top1_acc: 0.2500 top5_acc: 0.8125 loss_cls: 2.1946 2023/02/18 00:44:04 - mmengine - INFO - Epoch(train) [16][1160/1320] lr: 2.0000e-02 eta: 3:13:31 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 4.3586 loss: 1.8158 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8158 2023/02/18 00:44:09 - mmengine - INFO - Epoch(train) [16][1180/1320] lr: 2.0000e-02 eta: 3:13:25 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.4371 loss: 2.1022 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1022 2023/02/18 00:44:14 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:44:14 - mmengine - INFO - Epoch(train) [16][1200/1320] lr: 2.0000e-02 eta: 3:13:20 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.3781 loss: 2.0064 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0064 2023/02/18 00:44:19 - mmengine - INFO - Epoch(train) [16][1220/1320] lr: 2.0000e-02 eta: 3:13:15 time: 0.2547 data_time: 0.0102 memory: 13708 grad_norm: 4.3310 loss: 2.1673 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.1673 2023/02/18 00:44:24 - mmengine - INFO - Epoch(train) [16][1240/1320] lr: 2.0000e-02 eta: 3:13:10 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.3034 loss: 2.0694 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0694 2023/02/18 00:44:29 - mmengine - INFO - Epoch(train) [16][1260/1320] lr: 2.0000e-02 eta: 3:13:04 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 4.2412 loss: 2.2098 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.2098 2023/02/18 00:44:34 - mmengine - INFO - Epoch(train) [16][1280/1320] lr: 2.0000e-02 eta: 3:12:59 time: 0.2549 data_time: 0.0101 memory: 13708 grad_norm: 4.3198 loss: 2.1121 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1121 2023/02/18 00:44:40 - mmengine - INFO - Epoch(train) [16][1300/1320] lr: 2.0000e-02 eta: 3:12:54 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.2605 loss: 1.9265 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 1.9265 2023/02/18 00:44:45 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:44:45 - mmengine - INFO - Epoch(train) [16][1320/1320] lr: 2.0000e-02 eta: 3:12:48 time: 0.2511 data_time: 0.0106 memory: 13708 grad_norm: 4.3947 loss: 2.1168 top1_acc: 0.4545 top5_acc: 0.6364 loss_cls: 2.1168 2023/02/18 00:44:47 - mmengine - INFO - Epoch(val) [16][ 20/194] eta: 0:00:21 time: 0.1250 data_time: 0.0573 memory: 1818 2023/02/18 00:44:49 - mmengine - INFO - Epoch(val) [16][ 40/194] eta: 0:00:16 time: 0.0868 data_time: 0.0191 memory: 1818 2023/02/18 00:44:51 - mmengine - INFO - Epoch(val) [16][ 60/194] eta: 0:00:13 time: 0.0870 data_time: 0.0193 memory: 1818 2023/02/18 00:44:52 - mmengine - INFO - Epoch(val) [16][ 80/194] eta: 0:00:11 time: 0.0872 data_time: 0.0189 memory: 1818 2023/02/18 00:44:54 - mmengine - INFO - Epoch(val) [16][100/194] eta: 0:00:08 time: 0.0922 data_time: 0.0240 memory: 1818 2023/02/18 00:44:56 - mmengine - INFO - Epoch(val) [16][120/194] eta: 0:00:06 time: 0.0842 data_time: 0.0159 memory: 1818 2023/02/18 00:44:58 - mmengine - INFO - Epoch(val) [16][140/194] eta: 0:00:05 time: 0.0897 data_time: 0.0223 memory: 1818 2023/02/18 00:44:59 - mmengine - INFO - Epoch(val) [16][160/194] eta: 0:00:03 time: 0.0807 data_time: 0.0128 memory: 1818 2023/02/18 00:45:01 - mmengine - INFO - Epoch(val) [16][180/194] eta: 0:00:01 time: 0.0900 data_time: 0.0208 memory: 1818 2023/02/18 00:45:03 - mmengine - INFO - Epoch(val) [16][194/194] acc/top1: 0.4411 acc/top5: 0.7457 acc/mean1: 0.3693 2023/02/18 00:45:09 - mmengine - INFO - Epoch(train) [17][ 20/1320] lr: 2.0000e-02 eta: 3:12:45 time: 0.2982 data_time: 0.0445 memory: 13708 grad_norm: 4.2963 loss: 2.0035 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.0035 2023/02/18 00:45:14 - mmengine - INFO - Epoch(train) [17][ 40/1320] lr: 2.0000e-02 eta: 3:12:40 time: 0.2549 data_time: 0.0111 memory: 13708 grad_norm: 4.4373 loss: 1.9698 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9698 2023/02/18 00:45:19 - mmengine - INFO - Epoch(train) [17][ 60/1320] lr: 2.0000e-02 eta: 3:12:34 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.4232 loss: 2.0328 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.0328 2023/02/18 00:45:24 - mmengine - INFO - Epoch(train) [17][ 80/1320] lr: 2.0000e-02 eta: 3:12:29 time: 0.2544 data_time: 0.0102 memory: 13708 grad_norm: 4.3940 loss: 2.0943 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.0943 2023/02/18 00:45:29 - mmengine - INFO - Epoch(train) [17][ 100/1320] lr: 2.0000e-02 eta: 3:12:24 time: 0.2548 data_time: 0.0103 memory: 13708 grad_norm: 4.4057 loss: 2.0352 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.0352 2023/02/18 00:45:34 - mmengine - INFO - Epoch(train) [17][ 120/1320] lr: 2.0000e-02 eta: 3:12:19 time: 0.2555 data_time: 0.0106 memory: 13708 grad_norm: 4.4322 loss: 2.1968 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1968 2023/02/18 00:45:40 - mmengine - INFO - Epoch(train) [17][ 140/1320] lr: 2.0000e-02 eta: 3:12:13 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.3912 loss: 2.0651 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.0651 2023/02/18 00:45:45 - mmengine - INFO - Epoch(train) [17][ 160/1320] lr: 2.0000e-02 eta: 3:12:08 time: 0.2546 data_time: 0.0103 memory: 13708 grad_norm: 4.3770 loss: 1.8937 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8937 2023/02/18 00:45:50 - mmengine - INFO - Epoch(train) [17][ 180/1320] lr: 2.0000e-02 eta: 3:12:03 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.4355 loss: 1.9362 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 1.9362 2023/02/18 00:45:55 - mmengine - INFO - Epoch(train) [17][ 200/1320] lr: 2.0000e-02 eta: 3:11:57 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.4989 loss: 2.2280 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.2280 2023/02/18 00:46:00 - mmengine - INFO - Epoch(train) [17][ 220/1320] lr: 2.0000e-02 eta: 3:11:52 time: 0.2544 data_time: 0.0099 memory: 13708 grad_norm: 4.4102 loss: 1.9909 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.9909 2023/02/18 00:46:05 - mmengine - INFO - Epoch(train) [17][ 240/1320] lr: 2.0000e-02 eta: 3:11:47 time: 0.2548 data_time: 0.0104 memory: 13708 grad_norm: 4.5828 loss: 2.1678 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.1678 2023/02/18 00:46:10 - mmengine - INFO - Epoch(train) [17][ 260/1320] lr: 2.0000e-02 eta: 3:11:42 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.4219 loss: 2.2012 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.2012 2023/02/18 00:46:15 - mmengine - INFO - Epoch(train) [17][ 280/1320] lr: 2.0000e-02 eta: 3:11:36 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.4086 loss: 1.9479 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.9479 2023/02/18 00:46:20 - mmengine - INFO - Epoch(train) [17][ 300/1320] lr: 2.0000e-02 eta: 3:11:31 time: 0.2547 data_time: 0.0108 memory: 13708 grad_norm: 4.1909 loss: 1.8802 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8802 2023/02/18 00:46:25 - mmengine - INFO - Epoch(train) [17][ 320/1320] lr: 2.0000e-02 eta: 3:11:26 time: 0.2541 data_time: 0.0105 memory: 13708 grad_norm: 4.4011 loss: 2.1782 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1782 2023/02/18 00:46:31 - mmengine - INFO - Epoch(train) [17][ 340/1320] lr: 2.0000e-02 eta: 3:11:20 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.4197 loss: 2.0106 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0106 2023/02/18 00:46:36 - mmengine - INFO - Epoch(train) [17][ 360/1320] lr: 2.0000e-02 eta: 3:11:15 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.3699 loss: 2.1145 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 2.1145 2023/02/18 00:46:41 - mmengine - INFO - Epoch(train) [17][ 380/1320] lr: 2.0000e-02 eta: 3:11:10 time: 0.2546 data_time: 0.0100 memory: 13708 grad_norm: 4.3784 loss: 1.8768 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8768 2023/02/18 00:46:46 - mmengine - INFO - Epoch(train) [17][ 400/1320] lr: 2.0000e-02 eta: 3:11:05 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.4194 loss: 2.2505 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.2505 2023/02/18 00:46:51 - mmengine - INFO - Epoch(train) [17][ 420/1320] lr: 2.0000e-02 eta: 3:10:59 time: 0.2549 data_time: 0.0108 memory: 13708 grad_norm: 4.4091 loss: 2.0306 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0306 2023/02/18 00:46:57 - mmengine - INFO - Epoch(train) [17][ 440/1320] lr: 2.0000e-02 eta: 3:10:56 time: 0.2950 data_time: 0.0503 memory: 13708 grad_norm: 4.4080 loss: 1.9296 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9296 2023/02/18 00:47:02 - mmengine - INFO - Epoch(train) [17][ 460/1320] lr: 2.0000e-02 eta: 3:10:50 time: 0.2558 data_time: 0.0117 memory: 13708 grad_norm: 4.4111 loss: 1.8473 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.8473 2023/02/18 00:47:07 - mmengine - INFO - Epoch(train) [17][ 480/1320] lr: 2.0000e-02 eta: 3:10:45 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.4780 loss: 2.1073 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.1073 2023/02/18 00:47:12 - mmengine - INFO - Epoch(train) [17][ 500/1320] lr: 2.0000e-02 eta: 3:10:40 time: 0.2552 data_time: 0.0105 memory: 13708 grad_norm: 4.4857 loss: 1.9353 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9353 2023/02/18 00:47:17 - mmengine - INFO - Epoch(train) [17][ 520/1320] lr: 2.0000e-02 eta: 3:10:35 time: 0.2552 data_time: 0.0112 memory: 13708 grad_norm: 4.3916 loss: 2.1281 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1281 2023/02/18 00:47:22 - mmengine - INFO - Epoch(train) [17][ 540/1320] lr: 2.0000e-02 eta: 3:10:29 time: 0.2566 data_time: 0.0102 memory: 13708 grad_norm: 4.2971 loss: 2.1073 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.1073 2023/02/18 00:47:28 - mmengine - INFO - Epoch(train) [17][ 560/1320] lr: 2.0000e-02 eta: 3:10:24 time: 0.2565 data_time: 0.0112 memory: 13708 grad_norm: 4.3669 loss: 2.1118 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 2.1118 2023/02/18 00:47:33 - mmengine - INFO - Epoch(train) [17][ 580/1320] lr: 2.0000e-02 eta: 3:10:19 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.4889 loss: 2.1109 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1109 2023/02/18 00:47:38 - mmengine - INFO - Epoch(train) [17][ 600/1320] lr: 2.0000e-02 eta: 3:10:14 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.3832 loss: 2.1028 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.1028 2023/02/18 00:47:43 - mmengine - INFO - Epoch(train) [17][ 620/1320] lr: 2.0000e-02 eta: 3:10:08 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 4.3735 loss: 2.0464 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.0464 2023/02/18 00:47:48 - mmengine - INFO - Epoch(train) [17][ 640/1320] lr: 2.0000e-02 eta: 3:10:03 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.4878 loss: 1.9524 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 1.9524 2023/02/18 00:47:53 - mmengine - INFO - Epoch(train) [17][ 660/1320] lr: 2.0000e-02 eta: 3:09:58 time: 0.2553 data_time: 0.0113 memory: 13708 grad_norm: 4.4343 loss: 2.0396 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0396 2023/02/18 00:47:58 - mmengine - INFO - Epoch(train) [17][ 680/1320] lr: 2.0000e-02 eta: 3:09:53 time: 0.2546 data_time: 0.0106 memory: 13708 grad_norm: 4.4759 loss: 2.1345 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.1345 2023/02/18 00:48:03 - mmengine - INFO - Epoch(train) [17][ 700/1320] lr: 2.0000e-02 eta: 3:09:47 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 4.4536 loss: 2.1840 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1840 2023/02/18 00:48:08 - mmengine - INFO - Epoch(train) [17][ 720/1320] lr: 2.0000e-02 eta: 3:09:42 time: 0.2571 data_time: 0.0131 memory: 13708 grad_norm: 4.4396 loss: 1.8594 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8594 2023/02/18 00:48:14 - mmengine - INFO - Epoch(train) [17][ 740/1320] lr: 2.0000e-02 eta: 3:09:37 time: 0.2545 data_time: 0.0103 memory: 13708 grad_norm: 4.4461 loss: 2.0784 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.0784 2023/02/18 00:48:19 - mmengine - INFO - Epoch(train) [17][ 760/1320] lr: 2.0000e-02 eta: 3:09:32 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.5623 loss: 2.0377 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0377 2023/02/18 00:48:24 - mmengine - INFO - Epoch(train) [17][ 780/1320] lr: 2.0000e-02 eta: 3:09:26 time: 0.2551 data_time: 0.0107 memory: 13708 grad_norm: 4.3704 loss: 2.3033 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3033 2023/02/18 00:48:29 - mmengine - INFO - Epoch(train) [17][ 800/1320] lr: 2.0000e-02 eta: 3:09:21 time: 0.2551 data_time: 0.0103 memory: 13708 grad_norm: 4.1914 loss: 1.9648 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9648 2023/02/18 00:48:34 - mmengine - INFO - Epoch(train) [17][ 820/1320] lr: 2.0000e-02 eta: 3:09:16 time: 0.2574 data_time: 0.0131 memory: 13708 grad_norm: 4.3813 loss: 1.9483 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 1.9483 2023/02/18 00:48:39 - mmengine - INFO - Epoch(train) [17][ 840/1320] lr: 2.0000e-02 eta: 3:09:11 time: 0.2555 data_time: 0.0114 memory: 13708 grad_norm: 4.3973 loss: 2.0117 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0117 2023/02/18 00:48:44 - mmengine - INFO - Epoch(train) [17][ 860/1320] lr: 2.0000e-02 eta: 3:09:06 time: 0.2549 data_time: 0.0103 memory: 13708 grad_norm: 4.4755 loss: 2.0321 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0321 2023/02/18 00:48:49 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:48:49 - mmengine - INFO - Epoch(train) [17][ 880/1320] lr: 2.0000e-02 eta: 3:09:00 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 4.3849 loss: 2.0173 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0173 2023/02/18 00:48:54 - mmengine - INFO - Epoch(train) [17][ 900/1320] lr: 2.0000e-02 eta: 3:08:55 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.3737 loss: 2.1153 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1153 2023/02/18 00:49:00 - mmengine - INFO - Epoch(train) [17][ 920/1320] lr: 2.0000e-02 eta: 3:08:50 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.4087 loss: 2.0871 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0871 2023/02/18 00:49:05 - mmengine - INFO - Epoch(train) [17][ 940/1320] lr: 2.0000e-02 eta: 3:08:44 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.4487 loss: 2.1026 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.1026 2023/02/18 00:49:10 - mmengine - INFO - Epoch(train) [17][ 960/1320] lr: 2.0000e-02 eta: 3:08:39 time: 0.2548 data_time: 0.0104 memory: 13708 grad_norm: 4.4253 loss: 2.0794 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0794 2023/02/18 00:49:15 - mmengine - INFO - Epoch(train) [17][ 980/1320] lr: 2.0000e-02 eta: 3:08:34 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 4.4973 loss: 2.0827 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.0827 2023/02/18 00:49:20 - mmengine - INFO - Epoch(train) [17][1000/1320] lr: 2.0000e-02 eta: 3:08:29 time: 0.2553 data_time: 0.0104 memory: 13708 grad_norm: 4.3785 loss: 1.8748 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8748 2023/02/18 00:49:25 - mmengine - INFO - Epoch(train) [17][1020/1320] lr: 2.0000e-02 eta: 3:08:23 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.5246 loss: 1.9416 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9416 2023/02/18 00:49:30 - mmengine - INFO - Epoch(train) [17][1040/1320] lr: 2.0000e-02 eta: 3:08:18 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.3197 loss: 1.9776 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 1.9776 2023/02/18 00:49:35 - mmengine - INFO - Epoch(train) [17][1060/1320] lr: 2.0000e-02 eta: 3:08:13 time: 0.2546 data_time: 0.0105 memory: 13708 grad_norm: 4.3741 loss: 1.9984 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.9984 2023/02/18 00:49:40 - mmengine - INFO - Epoch(train) [17][1080/1320] lr: 2.0000e-02 eta: 3:08:08 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.4039 loss: 2.1508 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.1508 2023/02/18 00:49:45 - mmengine - INFO - Epoch(train) [17][1100/1320] lr: 2.0000e-02 eta: 3:08:02 time: 0.2558 data_time: 0.0106 memory: 13708 grad_norm: 4.3955 loss: 1.9997 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9997 2023/02/18 00:49:51 - mmengine - INFO - Epoch(train) [17][1120/1320] lr: 2.0000e-02 eta: 3:07:57 time: 0.2549 data_time: 0.0108 memory: 13708 grad_norm: 4.3624 loss: 1.9850 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9850 2023/02/18 00:49:56 - mmengine - INFO - Epoch(train) [17][1140/1320] lr: 2.0000e-02 eta: 3:07:52 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.3162 loss: 2.0309 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0309 2023/02/18 00:50:01 - mmengine - INFO - Epoch(train) [17][1160/1320] lr: 2.0000e-02 eta: 3:07:47 time: 0.2557 data_time: 0.0112 memory: 13708 grad_norm: 4.4267 loss: 1.8744 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8744 2023/02/18 00:50:06 - mmengine - INFO - Epoch(train) [17][1180/1320] lr: 2.0000e-02 eta: 3:07:42 time: 0.2580 data_time: 0.0134 memory: 13708 grad_norm: 4.4490 loss: 1.7974 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.7974 2023/02/18 00:50:11 - mmengine - INFO - Epoch(train) [17][1200/1320] lr: 2.0000e-02 eta: 3:07:36 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 4.4220 loss: 2.3587 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.3587 2023/02/18 00:50:16 - mmengine - INFO - Epoch(train) [17][1220/1320] lr: 2.0000e-02 eta: 3:07:31 time: 0.2554 data_time: 0.0102 memory: 13708 grad_norm: 4.4884 loss: 2.0130 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0130 2023/02/18 00:50:21 - mmengine - INFO - Epoch(train) [17][1240/1320] lr: 2.0000e-02 eta: 3:07:26 time: 0.2552 data_time: 0.0105 memory: 13708 grad_norm: 4.3988 loss: 2.2662 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.2662 2023/02/18 00:50:26 - mmengine - INFO - Epoch(train) [17][1260/1320] lr: 2.0000e-02 eta: 3:07:21 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.4461 loss: 1.9488 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.9488 2023/02/18 00:50:32 - mmengine - INFO - Epoch(train) [17][1280/1320] lr: 2.0000e-02 eta: 3:07:16 time: 0.2647 data_time: 0.0206 memory: 13708 grad_norm: 4.5427 loss: 2.0494 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0494 2023/02/18 00:50:37 - mmengine - INFO - Epoch(train) [17][1300/1320] lr: 2.0000e-02 eta: 3:07:10 time: 0.2553 data_time: 0.0111 memory: 13708 grad_norm: 4.4033 loss: 2.0767 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0767 2023/02/18 00:50:42 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:50:42 - mmengine - INFO - Epoch(train) [17][1320/1320] lr: 2.0000e-02 eta: 3:07:05 time: 0.2505 data_time: 0.0104 memory: 13708 grad_norm: 4.3569 loss: 1.9167 top1_acc: 0.5455 top5_acc: 1.0000 loss_cls: 1.9167 2023/02/18 00:50:44 - mmengine - INFO - Epoch(val) [17][ 20/194] eta: 0:00:22 time: 0.1289 data_time: 0.0605 memory: 1818 2023/02/18 00:50:46 - mmengine - INFO - Epoch(val) [17][ 40/194] eta: 0:00:16 time: 0.0878 data_time: 0.0196 memory: 1818 2023/02/18 00:50:48 - mmengine - INFO - Epoch(val) [17][ 60/194] eta: 0:00:13 time: 0.0884 data_time: 0.0200 memory: 1818 2023/02/18 00:50:50 - mmengine - INFO - Epoch(val) [17][ 80/194] eta: 0:00:11 time: 0.0863 data_time: 0.0181 memory: 1818 2023/02/18 00:50:51 - mmengine - INFO - Epoch(val) [17][100/194] eta: 0:00:09 time: 0.0919 data_time: 0.0240 memory: 1818 2023/02/18 00:50:53 - mmengine - INFO - Epoch(val) [17][120/194] eta: 0:00:07 time: 0.0855 data_time: 0.0171 memory: 1818 2023/02/18 00:50:56 - mmengine - INFO - Epoch(val) [17][140/194] eta: 0:00:05 time: 0.1423 data_time: 0.0127 memory: 1818 2023/02/18 00:50:58 - mmengine - INFO - Epoch(val) [17][160/194] eta: 0:00:03 time: 0.0834 data_time: 0.0147 memory: 1818 2023/02/18 00:50:59 - mmengine - INFO - Epoch(val) [17][180/194] eta: 0:00:01 time: 0.0816 data_time: 0.0135 memory: 1818 2023/02/18 00:51:01 - mmengine - INFO - Epoch(val) [17][194/194] acc/top1: 0.4518 acc/top5: 0.7433 acc/mean1: 0.3722 2023/02/18 00:51:07 - mmengine - INFO - Epoch(train) [18][ 20/1320] lr: 2.0000e-02 eta: 3:07:01 time: 0.2977 data_time: 0.0430 memory: 13708 grad_norm: 4.3643 loss: 1.9355 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.9355 2023/02/18 00:51:12 - mmengine - INFO - Epoch(train) [18][ 40/1320] lr: 2.0000e-02 eta: 3:06:56 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.2891 loss: 1.8833 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8833 2023/02/18 00:51:17 - mmengine - INFO - Epoch(train) [18][ 60/1320] lr: 2.0000e-02 eta: 3:06:51 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 4.4185 loss: 1.9667 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9667 2023/02/18 00:51:22 - mmengine - INFO - Epoch(train) [18][ 80/1320] lr: 2.0000e-02 eta: 3:06:46 time: 0.2545 data_time: 0.0107 memory: 13708 grad_norm: 4.3921 loss: 1.8878 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.8878 2023/02/18 00:51:27 - mmengine - INFO - Epoch(train) [18][ 100/1320] lr: 2.0000e-02 eta: 3:06:40 time: 0.2550 data_time: 0.0104 memory: 13708 grad_norm: 4.3576 loss: 2.0132 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0132 2023/02/18 00:51:33 - mmengine - INFO - Epoch(train) [18][ 120/1320] lr: 2.0000e-02 eta: 3:06:35 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.5004 loss: 1.9323 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.9323 2023/02/18 00:51:38 - mmengine - INFO - Epoch(train) [18][ 140/1320] lr: 2.0000e-02 eta: 3:06:30 time: 0.2555 data_time: 0.0106 memory: 13708 grad_norm: 4.3494 loss: 1.8073 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8073 2023/02/18 00:51:43 - mmengine - INFO - Epoch(train) [18][ 160/1320] lr: 2.0000e-02 eta: 3:06:25 time: 0.2546 data_time: 0.0105 memory: 13708 grad_norm: 4.3555 loss: 2.1288 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.1288 2023/02/18 00:51:48 - mmengine - INFO - Epoch(train) [18][ 180/1320] lr: 2.0000e-02 eta: 3:06:19 time: 0.2545 data_time: 0.0104 memory: 13708 grad_norm: 4.4782 loss: 2.1193 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1193 2023/02/18 00:51:53 - mmengine - INFO - Epoch(train) [18][ 200/1320] lr: 2.0000e-02 eta: 3:06:14 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.5026 loss: 2.0497 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0497 2023/02/18 00:51:58 - mmengine - INFO - Epoch(train) [18][ 220/1320] lr: 2.0000e-02 eta: 3:06:09 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.4839 loss: 2.0017 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0017 2023/02/18 00:52:03 - mmengine - INFO - Epoch(train) [18][ 240/1320] lr: 2.0000e-02 eta: 3:06:04 time: 0.2547 data_time: 0.0105 memory: 13708 grad_norm: 4.4842 loss: 2.0140 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.0140 2023/02/18 00:52:08 - mmengine - INFO - Epoch(train) [18][ 260/1320] lr: 2.0000e-02 eta: 3:05:58 time: 0.2557 data_time: 0.0104 memory: 13708 grad_norm: 4.4811 loss: 1.9891 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9891 2023/02/18 00:52:13 - mmengine - INFO - Epoch(train) [18][ 280/1320] lr: 2.0000e-02 eta: 3:05:53 time: 0.2545 data_time: 0.0102 memory: 13708 grad_norm: 4.4364 loss: 2.0037 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.0037 2023/02/18 00:52:18 - mmengine - INFO - Epoch(train) [18][ 300/1320] lr: 2.0000e-02 eta: 3:05:48 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 4.3709 loss: 1.8798 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.8798 2023/02/18 00:52:24 - mmengine - INFO - Epoch(train) [18][ 320/1320] lr: 2.0000e-02 eta: 3:05:42 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.5513 loss: 1.9796 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9796 2023/02/18 00:52:29 - mmengine - INFO - Epoch(train) [18][ 340/1320] lr: 2.0000e-02 eta: 3:05:37 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.4782 loss: 1.8006 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8006 2023/02/18 00:52:34 - mmengine - INFO - Epoch(train) [18][ 360/1320] lr: 2.0000e-02 eta: 3:05:32 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.4568 loss: 2.0441 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0441 2023/02/18 00:52:39 - mmengine - INFO - Epoch(train) [18][ 380/1320] lr: 2.0000e-02 eta: 3:05:27 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 4.5063 loss: 1.8192 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8192 2023/02/18 00:52:44 - mmengine - INFO - Epoch(train) [18][ 400/1320] lr: 2.0000e-02 eta: 3:05:21 time: 0.2557 data_time: 0.0116 memory: 13708 grad_norm: 4.4825 loss: 1.9853 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.9853 2023/02/18 00:52:49 - mmengine - INFO - Epoch(train) [18][ 420/1320] lr: 2.0000e-02 eta: 3:05:16 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 4.4443 loss: 2.0589 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.0589 2023/02/18 00:52:54 - mmengine - INFO - Epoch(train) [18][ 440/1320] lr: 2.0000e-02 eta: 3:05:11 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.3972 loss: 2.0100 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0100 2023/02/18 00:52:59 - mmengine - INFO - Epoch(train) [18][ 460/1320] lr: 2.0000e-02 eta: 3:05:06 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 4.3621 loss: 2.1249 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.1249 2023/02/18 00:53:04 - mmengine - INFO - Epoch(train) [18][ 480/1320] lr: 2.0000e-02 eta: 3:05:01 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.5283 loss: 2.0260 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0260 2023/02/18 00:53:10 - mmengine - INFO - Epoch(train) [18][ 500/1320] lr: 2.0000e-02 eta: 3:04:55 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 4.4978 loss: 2.0412 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0412 2023/02/18 00:53:15 - mmengine - INFO - Epoch(train) [18][ 520/1320] lr: 2.0000e-02 eta: 3:04:50 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.5588 loss: 1.9690 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9690 2023/02/18 00:53:20 - mmengine - INFO - Epoch(train) [18][ 540/1320] lr: 2.0000e-02 eta: 3:04:45 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.4658 loss: 1.9500 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9500 2023/02/18 00:53:25 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:53:25 - mmengine - INFO - Epoch(train) [18][ 560/1320] lr: 2.0000e-02 eta: 3:04:40 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.4595 loss: 2.0874 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0874 2023/02/18 00:53:30 - mmengine - INFO - Epoch(train) [18][ 580/1320] lr: 2.0000e-02 eta: 3:04:34 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.4122 loss: 2.1418 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1418 2023/02/18 00:53:35 - mmengine - INFO - Epoch(train) [18][ 600/1320] lr: 2.0000e-02 eta: 3:04:29 time: 0.2557 data_time: 0.0117 memory: 13708 grad_norm: 4.4426 loss: 2.0363 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.0363 2023/02/18 00:53:40 - mmengine - INFO - Epoch(train) [18][ 620/1320] lr: 2.0000e-02 eta: 3:04:24 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.4079 loss: 1.9503 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9503 2023/02/18 00:53:45 - mmengine - INFO - Epoch(train) [18][ 640/1320] lr: 2.0000e-02 eta: 3:04:19 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.4007 loss: 1.9859 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9859 2023/02/18 00:53:50 - mmengine - INFO - Epoch(train) [18][ 660/1320] lr: 2.0000e-02 eta: 3:04:13 time: 0.2550 data_time: 0.0104 memory: 13708 grad_norm: 4.3901 loss: 2.1125 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1125 2023/02/18 00:53:56 - mmengine - INFO - Epoch(train) [18][ 680/1320] lr: 2.0000e-02 eta: 3:04:08 time: 0.2556 data_time: 0.0112 memory: 13708 grad_norm: 4.5686 loss: 2.1698 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.1698 2023/02/18 00:54:01 - mmengine - INFO - Epoch(train) [18][ 700/1320] lr: 2.0000e-02 eta: 3:04:03 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.4234 loss: 2.0021 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.0021 2023/02/18 00:54:06 - mmengine - INFO - Epoch(train) [18][ 720/1320] lr: 2.0000e-02 eta: 3:03:58 time: 0.2550 data_time: 0.0104 memory: 13708 grad_norm: 4.4858 loss: 2.1142 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1142 2023/02/18 00:54:11 - mmengine - INFO - Epoch(train) [18][ 740/1320] lr: 2.0000e-02 eta: 3:03:52 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.4628 loss: 2.1111 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.1111 2023/02/18 00:54:16 - mmengine - INFO - Epoch(train) [18][ 760/1320] lr: 2.0000e-02 eta: 3:03:47 time: 0.2543 data_time: 0.0104 memory: 13708 grad_norm: 4.4471 loss: 1.8911 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.8911 2023/02/18 00:54:21 - mmengine - INFO - Epoch(train) [18][ 780/1320] lr: 2.0000e-02 eta: 3:03:42 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.5113 loss: 1.7576 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.7576 2023/02/18 00:54:26 - mmengine - INFO - Epoch(train) [18][ 800/1320] lr: 2.0000e-02 eta: 3:03:37 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.5066 loss: 2.0231 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0231 2023/02/18 00:54:31 - mmengine - INFO - Epoch(train) [18][ 820/1320] lr: 2.0000e-02 eta: 3:03:31 time: 0.2564 data_time: 0.0119 memory: 13708 grad_norm: 4.4152 loss: 1.9160 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9160 2023/02/18 00:54:36 - mmengine - INFO - Epoch(train) [18][ 840/1320] lr: 2.0000e-02 eta: 3:03:26 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.3358 loss: 2.1541 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.1541 2023/02/18 00:54:41 - mmengine - INFO - Epoch(train) [18][ 860/1320] lr: 2.0000e-02 eta: 3:03:21 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.3296 loss: 1.9854 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9854 2023/02/18 00:54:47 - mmengine - INFO - Epoch(train) [18][ 880/1320] lr: 2.0000e-02 eta: 3:03:16 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 4.4028 loss: 2.0683 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0683 2023/02/18 00:54:52 - mmengine - INFO - Epoch(train) [18][ 900/1320] lr: 2.0000e-02 eta: 3:03:10 time: 0.2559 data_time: 0.0104 memory: 13708 grad_norm: 4.4345 loss: 1.8273 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8273 2023/02/18 00:54:57 - mmengine - INFO - Epoch(train) [18][ 920/1320] lr: 2.0000e-02 eta: 3:03:05 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.2682 loss: 1.8766 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8766 2023/02/18 00:55:02 - mmengine - INFO - Epoch(train) [18][ 940/1320] lr: 2.0000e-02 eta: 3:03:00 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 4.4111 loss: 2.0153 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.0153 2023/02/18 00:55:07 - mmengine - INFO - Epoch(train) [18][ 960/1320] lr: 2.0000e-02 eta: 3:02:55 time: 0.2550 data_time: 0.0109 memory: 13708 grad_norm: 4.3938 loss: 1.9555 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 1.9555 2023/02/18 00:55:12 - mmengine - INFO - Epoch(train) [18][ 980/1320] lr: 2.0000e-02 eta: 3:02:49 time: 0.2552 data_time: 0.0110 memory: 13708 grad_norm: 4.3221 loss: 1.9482 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9482 2023/02/18 00:55:17 - mmengine - INFO - Epoch(train) [18][1000/1320] lr: 2.0000e-02 eta: 3:02:44 time: 0.2563 data_time: 0.0113 memory: 13708 grad_norm: 4.4643 loss: 2.1434 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 2.1434 2023/02/18 00:55:22 - mmengine - INFO - Epoch(train) [18][1020/1320] lr: 2.0000e-02 eta: 3:02:39 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.4122 loss: 1.9774 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9774 2023/02/18 00:55:27 - mmengine - INFO - Epoch(train) [18][1040/1320] lr: 2.0000e-02 eta: 3:02:34 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 4.4398 loss: 1.9910 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9910 2023/02/18 00:55:33 - mmengine - INFO - Epoch(train) [18][1060/1320] lr: 2.0000e-02 eta: 3:02:29 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 4.3733 loss: 2.1818 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.1818 2023/02/18 00:55:38 - mmengine - INFO - Epoch(train) [18][1080/1320] lr: 2.0000e-02 eta: 3:02:23 time: 0.2545 data_time: 0.0102 memory: 13708 grad_norm: 4.4141 loss: 2.0345 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.0345 2023/02/18 00:55:43 - mmengine - INFO - Epoch(train) [18][1100/1320] lr: 2.0000e-02 eta: 3:02:18 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.4706 loss: 1.9835 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9835 2023/02/18 00:55:48 - mmengine - INFO - Epoch(train) [18][1120/1320] lr: 2.0000e-02 eta: 3:02:13 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.4095 loss: 1.9080 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9080 2023/02/18 00:55:53 - mmengine - INFO - Epoch(train) [18][1140/1320] lr: 2.0000e-02 eta: 3:02:08 time: 0.2547 data_time: 0.0103 memory: 13708 grad_norm: 4.4013 loss: 1.7914 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.7914 2023/02/18 00:55:58 - mmengine - INFO - Epoch(train) [18][1160/1320] lr: 2.0000e-02 eta: 3:02:02 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 4.3661 loss: 2.1842 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1842 2023/02/18 00:56:03 - mmengine - INFO - Epoch(train) [18][1180/1320] lr: 2.0000e-02 eta: 3:01:57 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.4595 loss: 2.0136 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 2.0136 2023/02/18 00:56:08 - mmengine - INFO - Epoch(train) [18][1200/1320] lr: 2.0000e-02 eta: 3:01:52 time: 0.2556 data_time: 0.0116 memory: 13708 grad_norm: 4.5230 loss: 2.0560 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0560 2023/02/18 00:56:13 - mmengine - INFO - Epoch(train) [18][1220/1320] lr: 2.0000e-02 eta: 3:01:47 time: 0.2568 data_time: 0.0120 memory: 13708 grad_norm: 4.4408 loss: 1.9878 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.9878 2023/02/18 00:56:19 - mmengine - INFO - Epoch(train) [18][1240/1320] lr: 2.0000e-02 eta: 3:01:41 time: 0.2542 data_time: 0.0101 memory: 13708 grad_norm: 4.4407 loss: 2.0717 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0717 2023/02/18 00:56:24 - mmengine - INFO - Epoch(train) [18][1260/1320] lr: 2.0000e-02 eta: 3:01:36 time: 0.2551 data_time: 0.0107 memory: 13708 grad_norm: 4.4730 loss: 1.9445 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9445 2023/02/18 00:56:29 - mmengine - INFO - Epoch(train) [18][1280/1320] lr: 2.0000e-02 eta: 3:01:31 time: 0.2566 data_time: 0.0106 memory: 13708 grad_norm: 4.4346 loss: 2.0097 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0097 2023/02/18 00:56:34 - mmengine - INFO - Epoch(train) [18][1300/1320] lr: 2.0000e-02 eta: 3:01:26 time: 0.2595 data_time: 0.0153 memory: 13708 grad_norm: 4.2573 loss: 1.9379 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9379 2023/02/18 00:56:39 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:56:39 - mmengine - INFO - Epoch(train) [18][1320/1320] lr: 2.0000e-02 eta: 3:01:21 time: 0.2508 data_time: 0.0106 memory: 13708 grad_norm: 4.4340 loss: 2.0600 top1_acc: 0.3636 top5_acc: 0.5455 loss_cls: 2.0600 2023/02/18 00:56:39 - mmengine - INFO - Saving checkpoint at 18 epochs 2023/02/18 00:56:43 - mmengine - INFO - Epoch(val) [18][ 20/194] eta: 0:00:22 time: 0.1299 data_time: 0.0613 memory: 1818 2023/02/18 00:56:45 - mmengine - INFO - Epoch(val) [18][ 40/194] eta: 0:00:16 time: 0.0867 data_time: 0.0187 memory: 1818 2023/02/18 00:56:46 - mmengine - INFO - Epoch(val) [18][ 60/194] eta: 0:00:13 time: 0.0888 data_time: 0.0209 memory: 1818 2023/02/18 00:56:48 - mmengine - INFO - Epoch(val) [18][ 80/194] eta: 0:00:11 time: 0.0889 data_time: 0.0189 memory: 1818 2023/02/18 00:56:50 - mmengine - INFO - Epoch(val) [18][100/194] eta: 0:00:09 time: 0.0891 data_time: 0.0204 memory: 1818 2023/02/18 00:56:52 - mmengine - INFO - Epoch(val) [18][120/194] eta: 0:00:07 time: 0.0849 data_time: 0.0167 memory: 1818 2023/02/18 00:56:53 - mmengine - INFO - Epoch(val) [18][140/194] eta: 0:00:05 time: 0.0873 data_time: 0.0193 memory: 1818 2023/02/18 00:56:55 - mmengine - INFO - Epoch(val) [18][160/194] eta: 0:00:03 time: 0.0817 data_time: 0.0134 memory: 1818 2023/02/18 00:56:57 - mmengine - INFO - Epoch(val) [18][180/194] eta: 0:00:01 time: 0.0802 data_time: 0.0146 memory: 1818 2023/02/18 00:56:58 - mmengine - INFO - Epoch(val) [18][194/194] acc/top1: 0.4476 acc/top5: 0.7441 acc/mean1: 0.3849 2023/02/18 00:57:04 - mmengine - INFO - Epoch(train) [19][ 20/1320] lr: 2.0000e-02 eta: 3:01:17 time: 0.2962 data_time: 0.0431 memory: 13708 grad_norm: 4.4114 loss: 1.9596 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9596 2023/02/18 00:57:09 - mmengine - INFO - Epoch(train) [19][ 40/1320] lr: 2.0000e-02 eta: 3:01:11 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.4755 loss: 1.8111 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8111 2023/02/18 00:57:14 - mmengine - INFO - Epoch(train) [19][ 60/1320] lr: 2.0000e-02 eta: 3:01:06 time: 0.2545 data_time: 0.0103 memory: 13708 grad_norm: 4.3950 loss: 2.0887 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0887 2023/02/18 00:57:20 - mmengine - INFO - Epoch(train) [19][ 80/1320] lr: 2.0000e-02 eta: 3:01:01 time: 0.2546 data_time: 0.0106 memory: 13708 grad_norm: 4.5582 loss: 2.1898 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1898 2023/02/18 00:57:25 - mmengine - INFO - Epoch(train) [19][ 100/1320] lr: 2.0000e-02 eta: 3:00:56 time: 0.2545 data_time: 0.0104 memory: 13708 grad_norm: 4.3585 loss: 1.9667 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9667 2023/02/18 00:57:30 - mmengine - INFO - Epoch(train) [19][ 120/1320] lr: 2.0000e-02 eta: 3:00:50 time: 0.2552 data_time: 0.0103 memory: 13708 grad_norm: 4.3623 loss: 1.8323 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 1.8323 2023/02/18 00:57:35 - mmengine - INFO - Epoch(train) [19][ 140/1320] lr: 2.0000e-02 eta: 3:00:45 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 4.5170 loss: 1.8285 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.8285 2023/02/18 00:57:40 - mmengine - INFO - Epoch(train) [19][ 160/1320] lr: 2.0000e-02 eta: 3:00:40 time: 0.2590 data_time: 0.0131 memory: 13708 grad_norm: 4.3555 loss: 1.8367 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8367 2023/02/18 00:57:45 - mmengine - INFO - Epoch(train) [19][ 180/1320] lr: 2.0000e-02 eta: 3:00:35 time: 0.2578 data_time: 0.0124 memory: 13708 grad_norm: 4.4293 loss: 2.0660 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0660 2023/02/18 00:57:50 - mmengine - INFO - Epoch(train) [19][ 200/1320] lr: 2.0000e-02 eta: 3:00:30 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.4166 loss: 1.9394 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9394 2023/02/18 00:57:55 - mmengine - INFO - Epoch(train) [19][ 220/1320] lr: 2.0000e-02 eta: 3:00:24 time: 0.2546 data_time: 0.0105 memory: 13708 grad_norm: 4.3311 loss: 2.1858 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.1858 2023/02/18 00:58:00 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 00:58:00 - mmengine - INFO - Epoch(train) [19][ 240/1320] lr: 2.0000e-02 eta: 3:00:19 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.4241 loss: 2.0287 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 2.0287 2023/02/18 00:58:06 - mmengine - INFO - Epoch(train) [19][ 260/1320] lr: 2.0000e-02 eta: 3:00:14 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 4.5310 loss: 2.0317 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.0317 2023/02/18 00:58:11 - mmengine - INFO - Epoch(train) [19][ 280/1320] lr: 2.0000e-02 eta: 3:00:09 time: 0.2562 data_time: 0.0117 memory: 13708 grad_norm: 4.5170 loss: 1.8543 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.8543 2023/02/18 00:58:16 - mmengine - INFO - Epoch(train) [19][ 300/1320] lr: 2.0000e-02 eta: 3:00:03 time: 0.2543 data_time: 0.0102 memory: 13708 grad_norm: 4.4345 loss: 1.9973 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9973 2023/02/18 00:58:21 - mmengine - INFO - Epoch(train) [19][ 320/1320] lr: 2.0000e-02 eta: 2:59:58 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.5078 loss: 1.9361 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.9361 2023/02/18 00:58:26 - mmengine - INFO - Epoch(train) [19][ 340/1320] lr: 2.0000e-02 eta: 2:59:53 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.3525 loss: 2.1002 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1002 2023/02/18 00:58:31 - mmengine - INFO - Epoch(train) [19][ 360/1320] lr: 2.0000e-02 eta: 2:59:48 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.3463 loss: 1.8773 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.8773 2023/02/18 00:58:36 - mmengine - INFO - Epoch(train) [19][ 380/1320] lr: 2.0000e-02 eta: 2:59:43 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.4413 loss: 1.8567 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.8567 2023/02/18 00:58:41 - mmengine - INFO - Epoch(train) [19][ 400/1320] lr: 2.0000e-02 eta: 2:59:37 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.5260 loss: 2.0190 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0190 2023/02/18 00:58:46 - mmengine - INFO - Epoch(train) [19][ 420/1320] lr: 2.0000e-02 eta: 2:59:32 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.5126 loss: 2.0421 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0421 2023/02/18 00:58:51 - mmengine - INFO - Epoch(train) [19][ 440/1320] lr: 2.0000e-02 eta: 2:59:27 time: 0.2549 data_time: 0.0108 memory: 13708 grad_norm: 4.5024 loss: 2.1102 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1102 2023/02/18 00:58:57 - mmengine - INFO - Epoch(train) [19][ 460/1320] lr: 2.0000e-02 eta: 2:59:22 time: 0.2551 data_time: 0.0100 memory: 13708 grad_norm: 4.4675 loss: 1.9287 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9287 2023/02/18 00:59:02 - mmengine - INFO - Epoch(train) [19][ 480/1320] lr: 2.0000e-02 eta: 2:59:16 time: 0.2547 data_time: 0.0105 memory: 13708 grad_norm: 4.3740 loss: 1.8622 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8622 2023/02/18 00:59:07 - mmengine - INFO - Epoch(train) [19][ 500/1320] lr: 2.0000e-02 eta: 2:59:11 time: 0.2548 data_time: 0.0104 memory: 13708 grad_norm: 4.3990 loss: 1.9053 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9053 2023/02/18 00:59:12 - mmengine - INFO - Epoch(train) [19][ 520/1320] lr: 2.0000e-02 eta: 2:59:06 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.4378 loss: 1.9528 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.9528 2023/02/18 00:59:17 - mmengine - INFO - Epoch(train) [19][ 540/1320] lr: 2.0000e-02 eta: 2:59:01 time: 0.2545 data_time: 0.0104 memory: 13708 grad_norm: 4.5082 loss: 2.1075 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.1075 2023/02/18 00:59:22 - mmengine - INFO - Epoch(train) [19][ 560/1320] lr: 2.0000e-02 eta: 2:58:55 time: 0.2547 data_time: 0.0105 memory: 13708 grad_norm: 4.5481 loss: 2.2594 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2594 2023/02/18 00:59:27 - mmengine - INFO - Epoch(train) [19][ 580/1320] lr: 2.0000e-02 eta: 2:58:50 time: 0.2548 data_time: 0.0109 memory: 13708 grad_norm: 4.3831 loss: 2.1076 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.1076 2023/02/18 00:59:32 - mmengine - INFO - Epoch(train) [19][ 600/1320] lr: 2.0000e-02 eta: 2:58:45 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.4550 loss: 2.0865 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0865 2023/02/18 00:59:37 - mmengine - INFO - Epoch(train) [19][ 620/1320] lr: 2.0000e-02 eta: 2:58:40 time: 0.2547 data_time: 0.0103 memory: 13708 grad_norm: 4.4863 loss: 2.0163 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.0163 2023/02/18 00:59:42 - mmengine - INFO - Epoch(train) [19][ 640/1320] lr: 2.0000e-02 eta: 2:58:34 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 4.4293 loss: 2.0529 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0529 2023/02/18 00:59:48 - mmengine - INFO - Epoch(train) [19][ 660/1320] lr: 2.0000e-02 eta: 2:58:29 time: 0.2549 data_time: 0.0104 memory: 13708 grad_norm: 4.4255 loss: 1.9945 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 1.9945 2023/02/18 00:59:53 - mmengine - INFO - Epoch(train) [19][ 680/1320] lr: 2.0000e-02 eta: 2:58:24 time: 0.2552 data_time: 0.0104 memory: 13708 grad_norm: 4.4468 loss: 1.9522 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.9522 2023/02/18 00:59:58 - mmengine - INFO - Epoch(train) [19][ 700/1320] lr: 2.0000e-02 eta: 2:58:19 time: 0.2560 data_time: 0.0106 memory: 13708 grad_norm: 4.4397 loss: 2.1162 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.1162 2023/02/18 01:00:03 - mmengine - INFO - Epoch(train) [19][ 720/1320] lr: 2.0000e-02 eta: 2:58:13 time: 0.2541 data_time: 0.0103 memory: 13708 grad_norm: 4.3915 loss: 1.8867 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8867 2023/02/18 01:00:08 - mmengine - INFO - Epoch(train) [19][ 740/1320] lr: 2.0000e-02 eta: 2:58:08 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.4201 loss: 2.0249 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0249 2023/02/18 01:00:13 - mmengine - INFO - Epoch(train) [19][ 760/1320] lr: 2.0000e-02 eta: 2:58:03 time: 0.2556 data_time: 0.0112 memory: 13708 grad_norm: 4.4171 loss: 2.0649 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.0649 2023/02/18 01:00:18 - mmengine - INFO - Epoch(train) [19][ 780/1320] lr: 2.0000e-02 eta: 2:57:58 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.5027 loss: 2.3858 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.3858 2023/02/18 01:00:23 - mmengine - INFO - Epoch(train) [19][ 800/1320] lr: 2.0000e-02 eta: 2:57:52 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 4.4593 loss: 1.9677 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9677 2023/02/18 01:00:28 - mmengine - INFO - Epoch(train) [19][ 820/1320] lr: 2.0000e-02 eta: 2:57:47 time: 0.2558 data_time: 0.0118 memory: 13708 grad_norm: 4.2689 loss: 2.0087 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.0087 2023/02/18 01:00:34 - mmengine - INFO - Epoch(train) [19][ 840/1320] lr: 2.0000e-02 eta: 2:57:42 time: 0.2556 data_time: 0.0115 memory: 13708 grad_norm: 4.4423 loss: 2.0122 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0122 2023/02/18 01:00:39 - mmengine - INFO - Epoch(train) [19][ 860/1320] lr: 2.0000e-02 eta: 2:57:37 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.5094 loss: 2.0086 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0086 2023/02/18 01:00:44 - mmengine - INFO - Epoch(train) [19][ 880/1320] lr: 2.0000e-02 eta: 2:57:32 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 4.3938 loss: 1.9588 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9588 2023/02/18 01:00:49 - mmengine - INFO - Epoch(train) [19][ 900/1320] lr: 2.0000e-02 eta: 2:57:26 time: 0.2553 data_time: 0.0105 memory: 13708 grad_norm: 4.2354 loss: 2.0573 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.0573 2023/02/18 01:00:54 - mmengine - INFO - Epoch(train) [19][ 920/1320] lr: 2.0000e-02 eta: 2:57:21 time: 0.2561 data_time: 0.0114 memory: 13708 grad_norm: 4.4291 loss: 2.0411 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0411 2023/02/18 01:00:59 - mmengine - INFO - Epoch(train) [19][ 940/1320] lr: 2.0000e-02 eta: 2:57:16 time: 0.2547 data_time: 0.0103 memory: 13708 grad_norm: 4.4516 loss: 1.9510 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.9510 2023/02/18 01:01:04 - mmengine - INFO - Epoch(train) [19][ 960/1320] lr: 2.0000e-02 eta: 2:57:11 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 4.3822 loss: 2.1407 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 2.1407 2023/02/18 01:01:09 - mmengine - INFO - Epoch(train) [19][ 980/1320] lr: 2.0000e-02 eta: 2:57:05 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.5069 loss: 2.0323 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0323 2023/02/18 01:01:14 - mmengine - INFO - Epoch(train) [19][1000/1320] lr: 2.0000e-02 eta: 2:57:00 time: 0.2549 data_time: 0.0110 memory: 13708 grad_norm: 4.5742 loss: 1.9950 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9950 2023/02/18 01:01:20 - mmengine - INFO - Epoch(train) [19][1020/1320] lr: 2.0000e-02 eta: 2:56:55 time: 0.2558 data_time: 0.0118 memory: 13708 grad_norm: 4.3205 loss: 1.9657 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9657 2023/02/18 01:01:25 - mmengine - INFO - Epoch(train) [19][1040/1320] lr: 2.0000e-02 eta: 2:56:50 time: 0.2551 data_time: 0.0103 memory: 13708 grad_norm: 4.3097 loss: 1.8475 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8475 2023/02/18 01:01:30 - mmengine - INFO - Epoch(train) [19][1060/1320] lr: 2.0000e-02 eta: 2:56:45 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 4.3802 loss: 2.1985 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1985 2023/02/18 01:01:35 - mmengine - INFO - Epoch(train) [19][1080/1320] lr: 2.0000e-02 eta: 2:56:39 time: 0.2553 data_time: 0.0104 memory: 13708 grad_norm: 4.2588 loss: 2.1257 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.1257 2023/02/18 01:01:40 - mmengine - INFO - Epoch(train) [19][1100/1320] lr: 2.0000e-02 eta: 2:56:34 time: 0.2546 data_time: 0.0109 memory: 13708 grad_norm: 4.4202 loss: 2.1391 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1391 2023/02/18 01:01:45 - mmengine - INFO - Epoch(train) [19][1120/1320] lr: 2.0000e-02 eta: 2:56:29 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.3581 loss: 2.0427 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.0427 2023/02/18 01:01:50 - mmengine - INFO - Epoch(train) [19][1140/1320] lr: 2.0000e-02 eta: 2:56:24 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 4.3791 loss: 1.9827 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9827 2023/02/18 01:01:55 - mmengine - INFO - Epoch(train) [19][1160/1320] lr: 2.0000e-02 eta: 2:56:18 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.3292 loss: 1.7698 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.7698 2023/02/18 01:02:00 - mmengine - INFO - Epoch(train) [19][1180/1320] lr: 2.0000e-02 eta: 2:56:13 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.2790 loss: 1.8515 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.8515 2023/02/18 01:02:05 - mmengine - INFO - Epoch(train) [19][1200/1320] lr: 2.0000e-02 eta: 2:56:08 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.4784 loss: 2.1164 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.1164 2023/02/18 01:02:11 - mmengine - INFO - Epoch(train) [19][1220/1320] lr: 2.0000e-02 eta: 2:56:03 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 4.4308 loss: 2.0468 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.0468 2023/02/18 01:02:16 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:02:16 - mmengine - INFO - Epoch(train) [19][1240/1320] lr: 2.0000e-02 eta: 2:55:58 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 4.4631 loss: 2.1092 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1092 2023/02/18 01:02:21 - mmengine - INFO - Epoch(train) [19][1260/1320] lr: 2.0000e-02 eta: 2:55:52 time: 0.2551 data_time: 0.0103 memory: 13708 grad_norm: 4.3894 loss: 1.9593 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.9593 2023/02/18 01:02:26 - mmengine - INFO - Epoch(train) [19][1280/1320] lr: 2.0000e-02 eta: 2:55:47 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.3838 loss: 2.2299 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.2299 2023/02/18 01:02:31 - mmengine - INFO - Epoch(train) [19][1300/1320] lr: 2.0000e-02 eta: 2:55:42 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.4612 loss: 2.1900 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1900 2023/02/18 01:02:36 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:02:36 - mmengine - INFO - Epoch(train) [19][1320/1320] lr: 2.0000e-02 eta: 2:55:36 time: 0.2510 data_time: 0.0102 memory: 13708 grad_norm: 4.4808 loss: 1.8673 top1_acc: 0.8182 top5_acc: 0.8182 loss_cls: 1.8673 2023/02/18 01:02:39 - mmengine - INFO - Epoch(val) [19][ 20/194] eta: 0:00:21 time: 0.1240 data_time: 0.0561 memory: 1818 2023/02/18 01:02:41 - mmengine - INFO - Epoch(val) [19][ 40/194] eta: 0:00:17 time: 0.1083 data_time: 0.0204 memory: 1818 2023/02/18 01:02:42 - mmengine - INFO - Epoch(val) [19][ 60/194] eta: 0:00:14 time: 0.0815 data_time: 0.0136 memory: 1818 2023/02/18 01:02:44 - mmengine - INFO - Epoch(val) [19][ 80/194] eta: 0:00:11 time: 0.0843 data_time: 0.0154 memory: 1818 2023/02/18 01:02:46 - mmengine - INFO - Epoch(val) [19][100/194] eta: 0:00:09 time: 0.0822 data_time: 0.0140 memory: 1818 2023/02/18 01:02:47 - mmengine - INFO - Epoch(val) [19][120/194] eta: 0:00:06 time: 0.0808 data_time: 0.0127 memory: 1818 2023/02/18 01:02:49 - mmengine - INFO - Epoch(val) [19][140/194] eta: 0:00:05 time: 0.0912 data_time: 0.0216 memory: 1818 2023/02/18 01:02:51 - mmengine - INFO - Epoch(val) [19][160/194] eta: 0:00:03 time: 0.0815 data_time: 0.0128 memory: 1818 2023/02/18 01:02:53 - mmengine - INFO - Epoch(val) [19][180/194] eta: 0:00:01 time: 0.0903 data_time: 0.0221 memory: 1818 2023/02/18 01:02:54 - mmengine - INFO - Epoch(val) [19][194/194] acc/top1: 0.4400 acc/top5: 0.7365 acc/mean1: 0.3621 2023/02/18 01:03:00 - mmengine - INFO - Epoch(train) [20][ 20/1320] lr: 2.0000e-02 eta: 2:55:33 time: 0.3005 data_time: 0.0433 memory: 13708 grad_norm: 4.2358 loss: 2.0885 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0885 2023/02/18 01:03:06 - mmengine - INFO - Epoch(train) [20][ 40/1320] lr: 2.0000e-02 eta: 2:55:28 time: 0.2566 data_time: 0.0110 memory: 13708 grad_norm: 4.2962 loss: 1.9560 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9560 2023/02/18 01:03:11 - mmengine - INFO - Epoch(train) [20][ 60/1320] lr: 2.0000e-02 eta: 2:55:22 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 4.3637 loss: 1.8527 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.8527 2023/02/18 01:03:16 - mmengine - INFO - Epoch(train) [20][ 80/1320] lr: 2.0000e-02 eta: 2:55:17 time: 0.2545 data_time: 0.0107 memory: 13708 grad_norm: 4.3618 loss: 1.9623 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9623 2023/02/18 01:03:21 - mmengine - INFO - Epoch(train) [20][ 100/1320] lr: 2.0000e-02 eta: 2:55:12 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.3301 loss: 1.9287 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9287 2023/02/18 01:03:26 - mmengine - INFO - Epoch(train) [20][ 120/1320] lr: 2.0000e-02 eta: 2:55:07 time: 0.2548 data_time: 0.0104 memory: 13708 grad_norm: 4.4973 loss: 1.9527 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9527 2023/02/18 01:03:31 - mmengine - INFO - Epoch(train) [20][ 140/1320] lr: 2.0000e-02 eta: 2:55:01 time: 0.2548 data_time: 0.0100 memory: 13708 grad_norm: 4.4658 loss: 1.9778 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9778 2023/02/18 01:03:36 - mmengine - INFO - Epoch(train) [20][ 160/1320] lr: 2.0000e-02 eta: 2:54:56 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 4.4227 loss: 2.0670 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.0670 2023/02/18 01:03:41 - mmengine - INFO - Epoch(train) [20][ 180/1320] lr: 2.0000e-02 eta: 2:54:51 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.4818 loss: 1.9962 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9962 2023/02/18 01:03:46 - mmengine - INFO - Epoch(train) [20][ 200/1320] lr: 2.0000e-02 eta: 2:54:46 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.3494 loss: 1.9736 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9736 2023/02/18 01:03:52 - mmengine - INFO - Epoch(train) [20][ 220/1320] lr: 2.0000e-02 eta: 2:54:40 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.4607 loss: 1.8119 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.8119 2023/02/18 01:03:57 - mmengine - INFO - Epoch(train) [20][ 240/1320] lr: 2.0000e-02 eta: 2:54:35 time: 0.2564 data_time: 0.0108 memory: 13708 grad_norm: 4.5121 loss: 2.0815 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0815 2023/02/18 01:04:02 - mmengine - INFO - Epoch(train) [20][ 260/1320] lr: 2.0000e-02 eta: 2:54:30 time: 0.2557 data_time: 0.0115 memory: 13708 grad_norm: 4.5587 loss: 1.9168 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9168 2023/02/18 01:04:07 - mmengine - INFO - Epoch(train) [20][ 280/1320] lr: 2.0000e-02 eta: 2:54:25 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 4.5030 loss: 1.9628 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9628 2023/02/18 01:04:12 - mmengine - INFO - Epoch(train) [20][ 300/1320] lr: 2.0000e-02 eta: 2:54:20 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.3975 loss: 1.9061 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.9061 2023/02/18 01:04:17 - mmengine - INFO - Epoch(train) [20][ 320/1320] lr: 2.0000e-02 eta: 2:54:14 time: 0.2546 data_time: 0.0104 memory: 13708 grad_norm: 4.2798 loss: 1.8760 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.8760 2023/02/18 01:04:22 - mmengine - INFO - Epoch(train) [20][ 340/1320] lr: 2.0000e-02 eta: 2:54:09 time: 0.2650 data_time: 0.0210 memory: 13708 grad_norm: 4.3553 loss: 1.8629 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8629 2023/02/18 01:04:27 - mmengine - INFO - Epoch(train) [20][ 360/1320] lr: 2.0000e-02 eta: 2:54:04 time: 0.2544 data_time: 0.0103 memory: 13708 grad_norm: 4.4337 loss: 1.7874 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.7874 2023/02/18 01:04:33 - mmengine - INFO - Epoch(train) [20][ 380/1320] lr: 2.0000e-02 eta: 2:53:59 time: 0.2546 data_time: 0.0106 memory: 13708 grad_norm: 4.5246 loss: 1.8666 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.8666 2023/02/18 01:04:38 - mmengine - INFO - Epoch(train) [20][ 400/1320] lr: 2.0000e-02 eta: 2:53:54 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.5857 loss: 2.0085 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0085 2023/02/18 01:04:43 - mmengine - INFO - Epoch(train) [20][ 420/1320] lr: 2.0000e-02 eta: 2:53:49 time: 0.2553 data_time: 0.0104 memory: 13708 grad_norm: 4.3616 loss: 2.1947 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1947 2023/02/18 01:04:48 - mmengine - INFO - Epoch(train) [20][ 440/1320] lr: 2.0000e-02 eta: 2:53:43 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.4342 loss: 2.0210 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0210 2023/02/18 01:04:53 - mmengine - INFO - Epoch(train) [20][ 460/1320] lr: 2.0000e-02 eta: 2:53:38 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.4572 loss: 1.9414 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.9414 2023/02/18 01:04:58 - mmengine - INFO - Epoch(train) [20][ 480/1320] lr: 2.0000e-02 eta: 2:53:33 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.4625 loss: 1.9773 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9773 2023/02/18 01:05:03 - mmengine - INFO - Epoch(train) [20][ 500/1320] lr: 2.0000e-02 eta: 2:53:28 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.5008 loss: 2.0329 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.0329 2023/02/18 01:05:08 - mmengine - INFO - Epoch(train) [20][ 520/1320] lr: 2.0000e-02 eta: 2:53:22 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 4.4115 loss: 1.8412 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8412 2023/02/18 01:05:13 - mmengine - INFO - Epoch(train) [20][ 540/1320] lr: 2.0000e-02 eta: 2:53:17 time: 0.2562 data_time: 0.0116 memory: 13708 grad_norm: 4.3790 loss: 1.9475 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9475 2023/02/18 01:05:19 - mmengine - INFO - Epoch(train) [20][ 560/1320] lr: 2.0000e-02 eta: 2:53:12 time: 0.2556 data_time: 0.0111 memory: 13708 grad_norm: 4.3261 loss: 1.8651 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8651 2023/02/18 01:05:24 - mmengine - INFO - Epoch(train) [20][ 580/1320] lr: 2.0000e-02 eta: 2:53:07 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.5437 loss: 2.0221 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0221 2023/02/18 01:05:29 - mmengine - INFO - Epoch(train) [20][ 600/1320] lr: 2.0000e-02 eta: 2:53:02 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.4182 loss: 1.9035 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9035 2023/02/18 01:05:34 - mmengine - INFO - Epoch(train) [20][ 620/1320] lr: 2.0000e-02 eta: 2:52:56 time: 0.2575 data_time: 0.0128 memory: 13708 grad_norm: 4.4501 loss: 1.9324 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.9324 2023/02/18 01:05:39 - mmengine - INFO - Epoch(train) [20][ 640/1320] lr: 2.0000e-02 eta: 2:52:51 time: 0.2556 data_time: 0.0116 memory: 13708 grad_norm: 4.4185 loss: 2.0031 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0031 2023/02/18 01:05:44 - mmengine - INFO - Epoch(train) [20][ 660/1320] lr: 2.0000e-02 eta: 2:52:46 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.1810 loss: 2.2038 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.2038 2023/02/18 01:05:49 - mmengine - INFO - Epoch(train) [20][ 680/1320] lr: 2.0000e-02 eta: 2:52:41 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 4.4847 loss: 1.9709 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9709 2023/02/18 01:05:54 - mmengine - INFO - Epoch(train) [20][ 700/1320] lr: 2.0000e-02 eta: 2:52:36 time: 0.2547 data_time: 0.0105 memory: 13708 grad_norm: 4.5338 loss: 1.9895 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9895 2023/02/18 01:05:59 - mmengine - INFO - Epoch(train) [20][ 720/1320] lr: 2.0000e-02 eta: 2:52:30 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 4.4533 loss: 2.0814 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0814 2023/02/18 01:06:05 - mmengine - INFO - Epoch(train) [20][ 740/1320] lr: 2.0000e-02 eta: 2:52:25 time: 0.2557 data_time: 0.0102 memory: 13708 grad_norm: 4.4844 loss: 1.9677 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.9677 2023/02/18 01:06:11 - mmengine - INFO - Epoch(train) [20][ 760/1320] lr: 2.0000e-02 eta: 2:52:21 time: 0.2965 data_time: 0.0509 memory: 13708 grad_norm: 4.4161 loss: 1.9227 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9227 2023/02/18 01:06:16 - mmengine - INFO - Epoch(train) [20][ 780/1320] lr: 2.0000e-02 eta: 2:52:16 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.4589 loss: 2.1640 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1640 2023/02/18 01:06:21 - mmengine - INFO - Epoch(train) [20][ 800/1320] lr: 2.0000e-02 eta: 2:52:11 time: 0.2548 data_time: 0.0103 memory: 13708 grad_norm: 4.5438 loss: 1.9300 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9300 2023/02/18 01:06:26 - mmengine - INFO - Epoch(train) [20][ 820/1320] lr: 2.0000e-02 eta: 2:52:06 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.4800 loss: 1.9289 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.9289 2023/02/18 01:06:31 - mmengine - INFO - Epoch(train) [20][ 840/1320] lr: 2.0000e-02 eta: 2:52:00 time: 0.2558 data_time: 0.0112 memory: 13708 grad_norm: 4.3626 loss: 1.9615 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9615 2023/02/18 01:06:36 - mmengine - INFO - Epoch(train) [20][ 860/1320] lr: 2.0000e-02 eta: 2:51:55 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.4299 loss: 2.0214 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0214 2023/02/18 01:06:41 - mmengine - INFO - Epoch(train) [20][ 880/1320] lr: 2.0000e-02 eta: 2:51:50 time: 0.2555 data_time: 0.0110 memory: 13708 grad_norm: 4.5190 loss: 2.0122 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 2.0122 2023/02/18 01:06:46 - mmengine - INFO - Epoch(train) [20][ 900/1320] lr: 2.0000e-02 eta: 2:51:45 time: 0.2552 data_time: 0.0110 memory: 13708 grad_norm: 4.5401 loss: 2.2019 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.2019 2023/02/18 01:06:51 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:06:51 - mmengine - INFO - Epoch(train) [20][ 920/1320] lr: 2.0000e-02 eta: 2:51:39 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.4603 loss: 1.9943 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9943 2023/02/18 01:06:57 - mmengine - INFO - Epoch(train) [20][ 940/1320] lr: 2.0000e-02 eta: 2:51:35 time: 0.2650 data_time: 0.0203 memory: 13708 grad_norm: 4.3437 loss: 2.0444 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0444 2023/02/18 01:07:02 - mmengine - INFO - Epoch(train) [20][ 960/1320] lr: 2.0000e-02 eta: 2:51:29 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.3972 loss: 2.0211 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.0211 2023/02/18 01:07:07 - mmengine - INFO - Epoch(train) [20][ 980/1320] lr: 2.0000e-02 eta: 2:51:24 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.4739 loss: 1.9602 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9602 2023/02/18 01:07:12 - mmengine - INFO - Epoch(train) [20][1000/1320] lr: 2.0000e-02 eta: 2:51:19 time: 0.2560 data_time: 0.0111 memory: 13708 grad_norm: 4.5596 loss: 2.0391 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.0391 2023/02/18 01:07:17 - mmengine - INFO - Epoch(train) [20][1020/1320] lr: 2.0000e-02 eta: 2:51:14 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 4.3715 loss: 1.8997 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.8997 2023/02/18 01:07:22 - mmengine - INFO - Epoch(train) [20][1040/1320] lr: 2.0000e-02 eta: 2:51:08 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.3061 loss: 2.0771 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0771 2023/02/18 01:07:27 - mmengine - INFO - Epoch(train) [20][1060/1320] lr: 2.0000e-02 eta: 2:51:03 time: 0.2554 data_time: 0.0103 memory: 13708 grad_norm: 4.4297 loss: 1.9276 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9276 2023/02/18 01:07:32 - mmengine - INFO - Epoch(train) [20][1080/1320] lr: 2.0000e-02 eta: 2:50:58 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.4153 loss: 1.9686 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9686 2023/02/18 01:07:38 - mmengine - INFO - Epoch(train) [20][1100/1320] lr: 2.0000e-02 eta: 2:50:53 time: 0.2547 data_time: 0.0102 memory: 13708 grad_norm: 4.4743 loss: 1.9278 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9278 2023/02/18 01:07:43 - mmengine - INFO - Epoch(train) [20][1120/1320] lr: 2.0000e-02 eta: 2:50:48 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.2844 loss: 2.0564 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.0564 2023/02/18 01:07:48 - mmengine - INFO - Epoch(train) [20][1140/1320] lr: 2.0000e-02 eta: 2:50:42 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.4922 loss: 2.0229 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0229 2023/02/18 01:07:53 - mmengine - INFO - Epoch(train) [20][1160/1320] lr: 2.0000e-02 eta: 2:50:37 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.4492 loss: 1.9727 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9727 2023/02/18 01:07:58 - mmengine - INFO - Epoch(train) [20][1180/1320] lr: 2.0000e-02 eta: 2:50:32 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.4634 loss: 1.8720 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8720 2023/02/18 01:08:03 - mmengine - INFO - Epoch(train) [20][1200/1320] lr: 2.0000e-02 eta: 2:50:27 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 4.3632 loss: 1.8993 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.8993 2023/02/18 01:08:08 - mmengine - INFO - Epoch(train) [20][1220/1320] lr: 2.0000e-02 eta: 2:50:22 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.3645 loss: 1.9196 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9196 2023/02/18 01:08:13 - mmengine - INFO - Epoch(train) [20][1240/1320] lr: 2.0000e-02 eta: 2:50:16 time: 0.2580 data_time: 0.0126 memory: 13708 grad_norm: 4.3614 loss: 1.8363 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8363 2023/02/18 01:08:18 - mmengine - INFO - Epoch(train) [20][1260/1320] lr: 2.0000e-02 eta: 2:50:11 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.4228 loss: 1.7684 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.7684 2023/02/18 01:08:24 - mmengine - INFO - Epoch(train) [20][1280/1320] lr: 2.0000e-02 eta: 2:50:06 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.4822 loss: 1.9242 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 1.9242 2023/02/18 01:08:29 - mmengine - INFO - Epoch(train) [20][1300/1320] lr: 2.0000e-02 eta: 2:50:01 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 4.3583 loss: 1.8335 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.8335 2023/02/18 01:08:34 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:08:34 - mmengine - INFO - Epoch(train) [20][1320/1320] lr: 2.0000e-02 eta: 2:49:55 time: 0.2510 data_time: 0.0102 memory: 13708 grad_norm: 4.4405 loss: 2.0625 top1_acc: 0.4545 top5_acc: 0.7273 loss_cls: 2.0625 2023/02/18 01:08:36 - mmengine - INFO - Epoch(val) [20][ 20/194] eta: 0:00:21 time: 0.1249 data_time: 0.0564 memory: 1818 2023/02/18 01:08:38 - mmengine - INFO - Epoch(val) [20][ 40/194] eta: 0:00:16 time: 0.0878 data_time: 0.0195 memory: 1818 2023/02/18 01:08:40 - mmengine - INFO - Epoch(val) [20][ 60/194] eta: 0:00:13 time: 0.0876 data_time: 0.0197 memory: 1818 2023/02/18 01:08:41 - mmengine - INFO - Epoch(val) [20][ 80/194] eta: 0:00:10 time: 0.0833 data_time: 0.0153 memory: 1818 2023/02/18 01:08:43 - mmengine - INFO - Epoch(val) [20][100/194] eta: 0:00:08 time: 0.0911 data_time: 0.0236 memory: 1818 2023/02/18 01:08:45 - mmengine - INFO - Epoch(val) [20][120/194] eta: 0:00:06 time: 0.0879 data_time: 0.0174 memory: 1818 2023/02/18 01:08:47 - mmengine - INFO - Epoch(val) [20][140/194] eta: 0:00:04 time: 0.0850 data_time: 0.0165 memory: 1818 2023/02/18 01:08:49 - mmengine - INFO - Epoch(val) [20][160/194] eta: 0:00:03 time: 0.1032 data_time: 0.0145 memory: 1818 2023/02/18 01:08:50 - mmengine - INFO - Epoch(val) [20][180/194] eta: 0:00:01 time: 0.0823 data_time: 0.0152 memory: 1818 2023/02/18 01:08:52 - mmengine - INFO - Epoch(val) [20][194/194] acc/top1: 0.4515 acc/top5: 0.7425 acc/mean1: 0.3756 2023/02/18 01:08:58 - mmengine - INFO - Epoch(train) [21][ 20/1320] lr: 2.0000e-02 eta: 2:49:52 time: 0.3026 data_time: 0.0455 memory: 13708 grad_norm: 4.4285 loss: 1.9760 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.9760 2023/02/18 01:09:04 - mmengine - INFO - Epoch(train) [21][ 40/1320] lr: 2.0000e-02 eta: 2:49:46 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 4.4384 loss: 2.0777 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0777 2023/02/18 01:09:09 - mmengine - INFO - Epoch(train) [21][ 60/1320] lr: 2.0000e-02 eta: 2:49:41 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.4089 loss: 2.0235 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0235 2023/02/18 01:09:14 - mmengine - INFO - Epoch(train) [21][ 80/1320] lr: 2.0000e-02 eta: 2:49:36 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.4046 loss: 1.9458 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9458 2023/02/18 01:09:19 - mmengine - INFO - Epoch(train) [21][ 100/1320] lr: 2.0000e-02 eta: 2:49:31 time: 0.2569 data_time: 0.0114 memory: 13708 grad_norm: 4.5292 loss: 1.7571 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.7571 2023/02/18 01:09:24 - mmengine - INFO - Epoch(train) [21][ 120/1320] lr: 2.0000e-02 eta: 2:49:26 time: 0.2554 data_time: 0.0116 memory: 13708 grad_norm: 4.4363 loss: 2.0647 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0647 2023/02/18 01:09:29 - mmengine - INFO - Epoch(train) [21][ 140/1320] lr: 2.0000e-02 eta: 2:49:20 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.4150 loss: 1.9595 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9595 2023/02/18 01:09:34 - mmengine - INFO - Epoch(train) [21][ 160/1320] lr: 2.0000e-02 eta: 2:49:15 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.4271 loss: 1.7523 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.7523 2023/02/18 01:09:39 - mmengine - INFO - Epoch(train) [21][ 180/1320] lr: 2.0000e-02 eta: 2:49:10 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 4.4426 loss: 1.9774 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9774 2023/02/18 01:09:45 - mmengine - INFO - Epoch(train) [21][ 200/1320] lr: 2.0000e-02 eta: 2:49:05 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.5427 loss: 1.8610 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8610 2023/02/18 01:09:50 - mmengine - INFO - Epoch(train) [21][ 220/1320] lr: 2.0000e-02 eta: 2:49:00 time: 0.2552 data_time: 0.0102 memory: 13708 grad_norm: 4.4881 loss: 1.9586 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.9586 2023/02/18 01:09:55 - mmengine - INFO - Epoch(train) [21][ 240/1320] lr: 2.0000e-02 eta: 2:48:54 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.4161 loss: 2.1076 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1076 2023/02/18 01:10:00 - mmengine - INFO - Epoch(train) [21][ 260/1320] lr: 2.0000e-02 eta: 2:48:49 time: 0.2547 data_time: 0.0103 memory: 13708 grad_norm: 4.3313 loss: 1.8074 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8074 2023/02/18 01:10:05 - mmengine - INFO - Epoch(train) [21][ 280/1320] lr: 2.0000e-02 eta: 2:48:44 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.5323 loss: 2.1941 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.1941 2023/02/18 01:10:10 - mmengine - INFO - Epoch(train) [21][ 300/1320] lr: 2.0000e-02 eta: 2:48:39 time: 0.2554 data_time: 0.0114 memory: 13708 grad_norm: 4.4749 loss: 2.0691 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0691 2023/02/18 01:10:15 - mmengine - INFO - Epoch(train) [21][ 320/1320] lr: 2.0000e-02 eta: 2:48:33 time: 0.2553 data_time: 0.0105 memory: 13708 grad_norm: 4.3516 loss: 1.8157 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8157 2023/02/18 01:10:20 - mmengine - INFO - Epoch(train) [21][ 340/1320] lr: 2.0000e-02 eta: 2:48:28 time: 0.2555 data_time: 0.0112 memory: 13708 grad_norm: 4.3188 loss: 2.0468 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0468 2023/02/18 01:10:25 - mmengine - INFO - Epoch(train) [21][ 360/1320] lr: 2.0000e-02 eta: 2:48:23 time: 0.2554 data_time: 0.0115 memory: 13708 grad_norm: 4.4206 loss: 1.9317 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9317 2023/02/18 01:10:30 - mmengine - INFO - Epoch(train) [21][ 380/1320] lr: 2.0000e-02 eta: 2:48:18 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 4.4017 loss: 2.1862 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1862 2023/02/18 01:10:36 - mmengine - INFO - Epoch(train) [21][ 400/1320] lr: 2.0000e-02 eta: 2:48:13 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.4200 loss: 1.8711 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8711 2023/02/18 01:10:41 - mmengine - INFO - Epoch(train) [21][ 420/1320] lr: 2.0000e-02 eta: 2:48:07 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 4.5152 loss: 1.7043 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.7043 2023/02/18 01:10:46 - mmengine - INFO - Epoch(train) [21][ 440/1320] lr: 2.0000e-02 eta: 2:48:02 time: 0.2550 data_time: 0.0110 memory: 13708 grad_norm: 4.6580 loss: 2.1576 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.1576 2023/02/18 01:10:51 - mmengine - INFO - Epoch(train) [21][ 460/1320] lr: 2.0000e-02 eta: 2:47:57 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.4656 loss: 1.9484 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 1.9484 2023/02/18 01:10:56 - mmengine - INFO - Epoch(train) [21][ 480/1320] lr: 2.0000e-02 eta: 2:47:52 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.3382 loss: 2.0393 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0393 2023/02/18 01:11:01 - mmengine - INFO - Epoch(train) [21][ 500/1320] lr: 2.0000e-02 eta: 2:47:46 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.4215 loss: 1.8821 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8821 2023/02/18 01:11:06 - mmengine - INFO - Epoch(train) [21][ 520/1320] lr: 2.0000e-02 eta: 2:47:41 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.4608 loss: 1.9501 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9501 2023/02/18 01:11:11 - mmengine - INFO - Epoch(train) [21][ 540/1320] lr: 2.0000e-02 eta: 2:47:36 time: 0.2551 data_time: 0.0107 memory: 13708 grad_norm: 4.4388 loss: 2.0045 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 2.0045 2023/02/18 01:11:16 - mmengine - INFO - Epoch(train) [21][ 560/1320] lr: 2.0000e-02 eta: 2:47:31 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 4.3131 loss: 1.7480 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.7480 2023/02/18 01:11:22 - mmengine - INFO - Epoch(train) [21][ 580/1320] lr: 2.0000e-02 eta: 2:47:26 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 4.5233 loss: 2.0524 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.0524 2023/02/18 01:11:27 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:11:27 - mmengine - INFO - Epoch(train) [21][ 600/1320] lr: 2.0000e-02 eta: 2:47:20 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.4151 loss: 1.9757 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.9757 2023/02/18 01:11:32 - mmengine - INFO - Epoch(train) [21][ 620/1320] lr: 2.0000e-02 eta: 2:47:15 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.4566 loss: 2.0346 top1_acc: 0.3750 top5_acc: 0.9375 loss_cls: 2.0346 2023/02/18 01:11:37 - mmengine - INFO - Epoch(train) [21][ 640/1320] lr: 2.0000e-02 eta: 2:47:10 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 4.4613 loss: 1.9649 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9649 2023/02/18 01:11:42 - mmengine - INFO - Epoch(train) [21][ 660/1320] lr: 2.0000e-02 eta: 2:47:05 time: 0.2561 data_time: 0.0112 memory: 13708 grad_norm: 4.4730 loss: 2.0074 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0074 2023/02/18 01:11:47 - mmengine - INFO - Epoch(train) [21][ 680/1320] lr: 2.0000e-02 eta: 2:47:00 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 4.3974 loss: 1.9931 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 1.9931 2023/02/18 01:11:52 - mmengine - INFO - Epoch(train) [21][ 700/1320] lr: 2.0000e-02 eta: 2:46:54 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 4.4921 loss: 2.0030 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.0030 2023/02/18 01:11:57 - mmengine - INFO - Epoch(train) [21][ 720/1320] lr: 2.0000e-02 eta: 2:46:49 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 4.3838 loss: 1.9913 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9913 2023/02/18 01:12:02 - mmengine - INFO - Epoch(train) [21][ 740/1320] lr: 2.0000e-02 eta: 2:46:44 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.6299 loss: 1.9278 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.9278 2023/02/18 01:12:08 - mmengine - INFO - Epoch(train) [21][ 760/1320] lr: 2.0000e-02 eta: 2:46:39 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.5899 loss: 2.0521 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0521 2023/02/18 01:12:13 - mmengine - INFO - Epoch(train) [21][ 780/1320] lr: 2.0000e-02 eta: 2:46:34 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.4521 loss: 1.9886 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9886 2023/02/18 01:12:18 - mmengine - INFO - Epoch(train) [21][ 800/1320] lr: 2.0000e-02 eta: 2:46:28 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.4235 loss: 1.9509 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9509 2023/02/18 01:12:23 - mmengine - INFO - Epoch(train) [21][ 820/1320] lr: 2.0000e-02 eta: 2:46:23 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.4714 loss: 2.2966 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.2966 2023/02/18 01:12:28 - mmengine - INFO - Epoch(train) [21][ 840/1320] lr: 2.0000e-02 eta: 2:46:18 time: 0.2573 data_time: 0.0123 memory: 13708 grad_norm: 4.5697 loss: 2.0178 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0178 2023/02/18 01:12:33 - mmengine - INFO - Epoch(train) [21][ 860/1320] lr: 2.0000e-02 eta: 2:46:13 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.5290 loss: 2.0538 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0538 2023/02/18 01:12:38 - mmengine - INFO - Epoch(train) [21][ 880/1320] lr: 2.0000e-02 eta: 2:46:08 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.4302 loss: 2.0691 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0691 2023/02/18 01:12:43 - mmengine - INFO - Epoch(train) [21][ 900/1320] lr: 2.0000e-02 eta: 2:46:02 time: 0.2566 data_time: 0.0115 memory: 13708 grad_norm: 4.5200 loss: 2.0124 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 2.0124 2023/02/18 01:12:48 - mmengine - INFO - Epoch(train) [21][ 920/1320] lr: 2.0000e-02 eta: 2:45:57 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.3494 loss: 2.2509 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.2509 2023/02/18 01:12:54 - mmengine - INFO - Epoch(train) [21][ 940/1320] lr: 2.0000e-02 eta: 2:45:52 time: 0.2551 data_time: 0.0107 memory: 13708 grad_norm: 4.4224 loss: 1.9055 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9055 2023/02/18 01:12:59 - mmengine - INFO - Epoch(train) [21][ 960/1320] lr: 2.0000e-02 eta: 2:45:47 time: 0.2552 data_time: 0.0103 memory: 13708 grad_norm: 4.3790 loss: 2.0652 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0652 2023/02/18 01:13:04 - mmengine - INFO - Epoch(train) [21][ 980/1320] lr: 2.0000e-02 eta: 2:45:42 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.5243 loss: 2.0537 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0537 2023/02/18 01:13:09 - mmengine - INFO - Epoch(train) [21][1000/1320] lr: 2.0000e-02 eta: 2:45:36 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 4.3051 loss: 2.1726 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.1726 2023/02/18 01:13:14 - mmengine - INFO - Epoch(train) [21][1020/1320] lr: 2.0000e-02 eta: 2:45:31 time: 0.2564 data_time: 0.0112 memory: 13708 grad_norm: 4.4940 loss: 1.8017 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 1.8017 2023/02/18 01:13:19 - mmengine - INFO - Epoch(train) [21][1040/1320] lr: 2.0000e-02 eta: 2:45:26 time: 0.2549 data_time: 0.0104 memory: 13708 grad_norm: 4.4711 loss: 2.0268 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0268 2023/02/18 01:13:24 - mmengine - INFO - Epoch(train) [21][1060/1320] lr: 2.0000e-02 eta: 2:45:21 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 4.4902 loss: 1.7880 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.7880 2023/02/18 01:13:29 - mmengine - INFO - Epoch(train) [21][1080/1320] lr: 2.0000e-02 eta: 2:45:16 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.4002 loss: 2.0231 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0231 2023/02/18 01:13:34 - mmengine - INFO - Epoch(train) [21][1100/1320] lr: 2.0000e-02 eta: 2:45:10 time: 0.2560 data_time: 0.0112 memory: 13708 grad_norm: 4.3545 loss: 2.0113 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.0113 2023/02/18 01:13:40 - mmengine - INFO - Epoch(train) [21][1120/1320] lr: 2.0000e-02 eta: 2:45:05 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.5138 loss: 2.0349 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0349 2023/02/18 01:13:45 - mmengine - INFO - Epoch(train) [21][1140/1320] lr: 2.0000e-02 eta: 2:45:00 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 4.4661 loss: 2.0764 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 2.0764 2023/02/18 01:13:50 - mmengine - INFO - Epoch(train) [21][1160/1320] lr: 2.0000e-02 eta: 2:44:55 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 4.5373 loss: 2.0064 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0064 2023/02/18 01:13:55 - mmengine - INFO - Epoch(train) [21][1180/1320] lr: 2.0000e-02 eta: 2:44:50 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 4.4827 loss: 1.9568 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9568 2023/02/18 01:14:00 - mmengine - INFO - Epoch(train) [21][1200/1320] lr: 2.0000e-02 eta: 2:44:44 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 4.5191 loss: 2.2497 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.2497 2023/02/18 01:14:05 - mmengine - INFO - Epoch(train) [21][1220/1320] lr: 2.0000e-02 eta: 2:44:39 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.3725 loss: 1.8847 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8847 2023/02/18 01:14:10 - mmengine - INFO - Epoch(train) [21][1240/1320] lr: 2.0000e-02 eta: 2:44:34 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.3777 loss: 1.9417 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9417 2023/02/18 01:14:15 - mmengine - INFO - Epoch(train) [21][1260/1320] lr: 2.0000e-02 eta: 2:44:29 time: 0.2556 data_time: 0.0111 memory: 13708 grad_norm: 4.6166 loss: 1.8868 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.8868 2023/02/18 01:14:20 - mmengine - INFO - Epoch(train) [21][1280/1320] lr: 2.0000e-02 eta: 2:44:23 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.3833 loss: 2.1361 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 2.1361 2023/02/18 01:14:26 - mmengine - INFO - Epoch(train) [21][1300/1320] lr: 2.0000e-02 eta: 2:44:18 time: 0.2558 data_time: 0.0104 memory: 13708 grad_norm: 4.4453 loss: 2.1279 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1279 2023/02/18 01:14:31 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:14:31 - mmengine - INFO - Epoch(train) [21][1320/1320] lr: 2.0000e-02 eta: 2:44:13 time: 0.2516 data_time: 0.0108 memory: 13708 grad_norm: 4.3990 loss: 1.8209 top1_acc: 0.4545 top5_acc: 0.9091 loss_cls: 1.8209 2023/02/18 01:14:31 - mmengine - INFO - Saving checkpoint at 21 epochs 2023/02/18 01:14:34 - mmengine - INFO - Epoch(val) [21][ 20/194] eta: 0:00:21 time: 0.1253 data_time: 0.0566 memory: 1818 2023/02/18 01:14:36 - mmengine - INFO - Epoch(val) [21][ 40/194] eta: 0:00:16 time: 0.0883 data_time: 0.0195 memory: 1818 2023/02/18 01:14:38 - mmengine - INFO - Epoch(val) [21][ 60/194] eta: 0:00:14 time: 0.1068 data_time: 0.0195 memory: 1818 2023/02/18 01:14:40 - mmengine - INFO - Epoch(val) [21][ 80/194] eta: 0:00:11 time: 0.0820 data_time: 0.0138 memory: 1818 2023/02/18 01:14:42 - mmengine - INFO - Epoch(val) [21][100/194] eta: 0:00:09 time: 0.0862 data_time: 0.0178 memory: 1818 2023/02/18 01:14:43 - mmengine - INFO - Epoch(val) [21][120/194] eta: 0:00:07 time: 0.0855 data_time: 0.0154 memory: 1818 2023/02/18 01:14:45 - mmengine - INFO - Epoch(val) [21][140/194] eta: 0:00:05 time: 0.0852 data_time: 0.0165 memory: 1818 2023/02/18 01:14:47 - mmengine - INFO - Epoch(val) [21][160/194] eta: 0:00:03 time: 0.0835 data_time: 0.0149 memory: 1818 2023/02/18 01:14:48 - mmengine - INFO - Epoch(val) [21][180/194] eta: 0:00:01 time: 0.0776 data_time: 0.0115 memory: 1818 2023/02/18 01:14:50 - mmengine - INFO - Epoch(val) [21][194/194] acc/top1: 0.4743 acc/top5: 0.7645 acc/mean1: 0.4011 2023/02/18 01:14:50 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_15.pth is removed 2023/02/18 01:14:51 - mmengine - INFO - The best checkpoint with 0.4743 acc/top1 at 21 epoch is saved to best_acc/top1_epoch_21.pth. 2023/02/18 01:14:57 - mmengine - INFO - Epoch(train) [22][ 20/1320] lr: 2.0000e-02 eta: 2:44:09 time: 0.2920 data_time: 0.0391 memory: 13708 grad_norm: 4.4746 loss: 1.9192 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9192 2023/02/18 01:15:02 - mmengine - INFO - Epoch(train) [22][ 40/1320] lr: 2.0000e-02 eta: 2:44:04 time: 0.2562 data_time: 0.0112 memory: 13708 grad_norm: 4.2929 loss: 1.9245 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9245 2023/02/18 01:15:07 - mmengine - INFO - Epoch(train) [22][ 60/1320] lr: 2.0000e-02 eta: 2:43:58 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 4.3878 loss: 1.8272 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8272 2023/02/18 01:15:12 - mmengine - INFO - Epoch(train) [22][ 80/1320] lr: 2.0000e-02 eta: 2:43:53 time: 0.2561 data_time: 0.0112 memory: 13708 grad_norm: 4.5095 loss: 1.9632 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.9632 2023/02/18 01:15:17 - mmengine - INFO - Epoch(train) [22][ 100/1320] lr: 2.0000e-02 eta: 2:43:48 time: 0.2581 data_time: 0.0115 memory: 13708 grad_norm: 4.4606 loss: 1.8384 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8384 2023/02/18 01:15:22 - mmengine - INFO - Epoch(train) [22][ 120/1320] lr: 2.0000e-02 eta: 2:43:43 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.3535 loss: 1.9840 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9840 2023/02/18 01:15:27 - mmengine - INFO - Epoch(train) [22][ 140/1320] lr: 2.0000e-02 eta: 2:43:38 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.6272 loss: 1.9103 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.9103 2023/02/18 01:15:32 - mmengine - INFO - Epoch(train) [22][ 160/1320] lr: 2.0000e-02 eta: 2:43:32 time: 0.2542 data_time: 0.0096 memory: 13708 grad_norm: 4.5665 loss: 1.9168 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9168 2023/02/18 01:15:38 - mmengine - INFO - Epoch(train) [22][ 180/1320] lr: 2.0000e-02 eta: 2:43:27 time: 0.2545 data_time: 0.0104 memory: 13708 grad_norm: 4.4921 loss: 1.9220 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9220 2023/02/18 01:15:43 - mmengine - INFO - Epoch(train) [22][ 200/1320] lr: 2.0000e-02 eta: 2:43:22 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.5275 loss: 1.8896 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8896 2023/02/18 01:15:48 - mmengine - INFO - Epoch(train) [22][ 220/1320] lr: 2.0000e-02 eta: 2:43:17 time: 0.2546 data_time: 0.0105 memory: 13708 grad_norm: 4.4358 loss: 1.9219 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.9219 2023/02/18 01:15:53 - mmengine - INFO - Epoch(train) [22][ 240/1320] lr: 2.0000e-02 eta: 2:43:12 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.4517 loss: 1.9300 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.9300 2023/02/18 01:15:58 - mmengine - INFO - Epoch(train) [22][ 260/1320] lr: 2.0000e-02 eta: 2:43:06 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 4.4214 loss: 1.8543 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8543 2023/02/18 01:16:03 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:16:03 - mmengine - INFO - Epoch(train) [22][ 280/1320] lr: 2.0000e-02 eta: 2:43:01 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.5576 loss: 2.0721 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0721 2023/02/18 01:16:08 - mmengine - INFO - Epoch(train) [22][ 300/1320] lr: 2.0000e-02 eta: 2:42:56 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.3940 loss: 1.7774 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.7774 2023/02/18 01:16:13 - mmengine - INFO - Epoch(train) [22][ 320/1320] lr: 2.0000e-02 eta: 2:42:51 time: 0.2552 data_time: 0.0102 memory: 13708 grad_norm: 4.4540 loss: 1.8384 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8384 2023/02/18 01:16:18 - mmengine - INFO - Epoch(train) [22][ 340/1320] lr: 2.0000e-02 eta: 2:42:46 time: 0.2546 data_time: 0.0105 memory: 13708 grad_norm: 4.5142 loss: 1.8770 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.8770 2023/02/18 01:16:23 - mmengine - INFO - Epoch(train) [22][ 360/1320] lr: 2.0000e-02 eta: 2:42:40 time: 0.2553 data_time: 0.0111 memory: 13708 grad_norm: 4.5665 loss: 1.8451 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8451 2023/02/18 01:16:29 - mmengine - INFO - Epoch(train) [22][ 380/1320] lr: 2.0000e-02 eta: 2:42:35 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.5560 loss: 1.9775 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9775 2023/02/18 01:16:35 - mmengine - INFO - Epoch(train) [22][ 400/1320] lr: 2.0000e-02 eta: 2:42:31 time: 0.3092 data_time: 0.0103 memory: 13708 grad_norm: 4.3962 loss: 2.0143 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0143 2023/02/18 01:16:40 - mmengine - INFO - Epoch(train) [22][ 420/1320] lr: 2.0000e-02 eta: 2:42:26 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.3152 loss: 1.9118 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9118 2023/02/18 01:16:45 - mmengine - INFO - Epoch(train) [22][ 440/1320] lr: 2.0000e-02 eta: 2:42:21 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.5008 loss: 1.9010 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 1.9010 2023/02/18 01:16:50 - mmengine - INFO - Epoch(train) [22][ 460/1320] lr: 2.0000e-02 eta: 2:42:16 time: 0.2573 data_time: 0.0124 memory: 13708 grad_norm: 4.4403 loss: 2.0329 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0329 2023/02/18 01:16:55 - mmengine - INFO - Epoch(train) [22][ 480/1320] lr: 2.0000e-02 eta: 2:42:11 time: 0.2556 data_time: 0.0112 memory: 13708 grad_norm: 4.4578 loss: 1.7326 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.7326 2023/02/18 01:17:00 - mmengine - INFO - Epoch(train) [22][ 500/1320] lr: 2.0000e-02 eta: 2:42:05 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 4.3862 loss: 1.8573 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8573 2023/02/18 01:17:05 - mmengine - INFO - Epoch(train) [22][ 520/1320] lr: 2.0000e-02 eta: 2:42:00 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 4.4584 loss: 2.0588 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0588 2023/02/18 01:17:11 - mmengine - INFO - Epoch(train) [22][ 540/1320] lr: 2.0000e-02 eta: 2:41:55 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 4.3996 loss: 2.0592 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0592 2023/02/18 01:17:16 - mmengine - INFO - Epoch(train) [22][ 560/1320] lr: 2.0000e-02 eta: 2:41:50 time: 0.2547 data_time: 0.0104 memory: 13708 grad_norm: 4.3847 loss: 1.8799 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.8799 2023/02/18 01:17:21 - mmengine - INFO - Epoch(train) [22][ 580/1320] lr: 2.0000e-02 eta: 2:41:45 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 4.3664 loss: 2.0111 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0111 2023/02/18 01:17:26 - mmengine - INFO - Epoch(train) [22][ 600/1320] lr: 2.0000e-02 eta: 2:41:39 time: 0.2558 data_time: 0.0113 memory: 13708 grad_norm: 4.5345 loss: 1.9295 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.9295 2023/02/18 01:17:31 - mmengine - INFO - Epoch(train) [22][ 620/1320] lr: 2.0000e-02 eta: 2:41:34 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.5009 loss: 2.0567 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0567 2023/02/18 01:17:36 - mmengine - INFO - Epoch(train) [22][ 640/1320] lr: 2.0000e-02 eta: 2:41:29 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.4082 loss: 2.0729 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0729 2023/02/18 01:17:41 - mmengine - INFO - Epoch(train) [22][ 660/1320] lr: 2.0000e-02 eta: 2:41:24 time: 0.2564 data_time: 0.0121 memory: 13708 grad_norm: 4.3743 loss: 1.9335 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 1.9335 2023/02/18 01:17:46 - mmengine - INFO - Epoch(train) [22][ 680/1320] lr: 2.0000e-02 eta: 2:41:19 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.5817 loss: 2.0622 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.0622 2023/02/18 01:17:51 - mmengine - INFO - Epoch(train) [22][ 700/1320] lr: 2.0000e-02 eta: 2:41:13 time: 0.2549 data_time: 0.0104 memory: 13708 grad_norm: 4.5358 loss: 2.0672 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0672 2023/02/18 01:17:57 - mmengine - INFO - Epoch(train) [22][ 720/1320] lr: 2.0000e-02 eta: 2:41:08 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.4636 loss: 1.9889 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9889 2023/02/18 01:18:02 - mmengine - INFO - Epoch(train) [22][ 740/1320] lr: 2.0000e-02 eta: 2:41:03 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 4.5839 loss: 1.8721 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8721 2023/02/18 01:18:07 - mmengine - INFO - Epoch(train) [22][ 760/1320] lr: 2.0000e-02 eta: 2:40:58 time: 0.2557 data_time: 0.0104 memory: 13708 grad_norm: 4.4357 loss: 2.0204 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.0204 2023/02/18 01:18:12 - mmengine - INFO - Epoch(train) [22][ 780/1320] lr: 2.0000e-02 eta: 2:40:53 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 4.4243 loss: 1.9216 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.9216 2023/02/18 01:18:17 - mmengine - INFO - Epoch(train) [22][ 800/1320] lr: 2.0000e-02 eta: 2:40:47 time: 0.2552 data_time: 0.0105 memory: 13708 grad_norm: 4.4491 loss: 2.0198 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0198 2023/02/18 01:18:22 - mmengine - INFO - Epoch(train) [22][ 820/1320] lr: 2.0000e-02 eta: 2:40:42 time: 0.2555 data_time: 0.0113 memory: 13708 grad_norm: 4.4727 loss: 2.0185 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0185 2023/02/18 01:18:27 - mmengine - INFO - Epoch(train) [22][ 840/1320] lr: 2.0000e-02 eta: 2:40:37 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 4.4960 loss: 1.9806 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9806 2023/02/18 01:18:32 - mmengine - INFO - Epoch(train) [22][ 860/1320] lr: 2.0000e-02 eta: 2:40:32 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.5288 loss: 2.0532 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.0532 2023/02/18 01:18:37 - mmengine - INFO - Epoch(train) [22][ 880/1320] lr: 2.0000e-02 eta: 2:40:27 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 4.5471 loss: 2.0571 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0571 2023/02/18 01:18:43 - mmengine - INFO - Epoch(train) [22][ 900/1320] lr: 2.0000e-02 eta: 2:40:21 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 4.4404 loss: 2.0564 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0564 2023/02/18 01:18:48 - mmengine - INFO - Epoch(train) [22][ 920/1320] lr: 2.0000e-02 eta: 2:40:16 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.4916 loss: 1.8827 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.8827 2023/02/18 01:18:53 - mmengine - INFO - Epoch(train) [22][ 940/1320] lr: 2.0000e-02 eta: 2:40:11 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.4340 loss: 1.8215 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.8215 2023/02/18 01:18:58 - mmengine - INFO - Epoch(train) [22][ 960/1320] lr: 2.0000e-02 eta: 2:40:06 time: 0.2567 data_time: 0.0118 memory: 13708 grad_norm: 4.4382 loss: 1.8673 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8673 2023/02/18 01:19:03 - mmengine - INFO - Epoch(train) [22][ 980/1320] lr: 2.0000e-02 eta: 2:40:01 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 4.3724 loss: 1.6963 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.6963 2023/02/18 01:19:08 - mmengine - INFO - Epoch(train) [22][1000/1320] lr: 2.0000e-02 eta: 2:39:55 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.3846 loss: 1.9680 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.9680 2023/02/18 01:19:13 - mmengine - INFO - Epoch(train) [22][1020/1320] lr: 2.0000e-02 eta: 2:39:50 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.6020 loss: 2.1719 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.1719 2023/02/18 01:19:18 - mmengine - INFO - Epoch(train) [22][1040/1320] lr: 2.0000e-02 eta: 2:39:45 time: 0.2559 data_time: 0.0114 memory: 13708 grad_norm: 4.4778 loss: 1.9805 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9805 2023/02/18 01:19:23 - mmengine - INFO - Epoch(train) [22][1060/1320] lr: 2.0000e-02 eta: 2:39:40 time: 0.2552 data_time: 0.0111 memory: 13708 grad_norm: 4.5101 loss: 1.9462 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9462 2023/02/18 01:19:29 - mmengine - INFO - Epoch(train) [22][1080/1320] lr: 2.0000e-02 eta: 2:39:35 time: 0.2556 data_time: 0.0103 memory: 13708 grad_norm: 4.3470 loss: 1.9840 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.9840 2023/02/18 01:19:34 - mmengine - INFO - Epoch(train) [22][1100/1320] lr: 2.0000e-02 eta: 2:39:29 time: 0.2547 data_time: 0.0107 memory: 13708 grad_norm: 4.2717 loss: 2.0981 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0981 2023/02/18 01:19:39 - mmengine - INFO - Epoch(train) [22][1120/1320] lr: 2.0000e-02 eta: 2:39:24 time: 0.2573 data_time: 0.0121 memory: 13708 grad_norm: 4.4971 loss: 1.8996 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.8996 2023/02/18 01:19:44 - mmengine - INFO - Epoch(train) [22][1140/1320] lr: 2.0000e-02 eta: 2:39:19 time: 0.2573 data_time: 0.0124 memory: 13708 grad_norm: 4.4633 loss: 1.9812 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.9812 2023/02/18 01:19:49 - mmengine - INFO - Epoch(train) [22][1160/1320] lr: 2.0000e-02 eta: 2:39:14 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.4580 loss: 1.9877 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9877 2023/02/18 01:19:54 - mmengine - INFO - Epoch(train) [22][1180/1320] lr: 2.0000e-02 eta: 2:39:09 time: 0.2552 data_time: 0.0103 memory: 13708 grad_norm: 4.4207 loss: 1.9552 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9552 2023/02/18 01:19:59 - mmengine - INFO - Epoch(train) [22][1200/1320] lr: 2.0000e-02 eta: 2:39:03 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.3617 loss: 2.1364 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1364 2023/02/18 01:20:04 - mmengine - INFO - Epoch(train) [22][1220/1320] lr: 2.0000e-02 eta: 2:38:58 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 4.5591 loss: 2.0216 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0216 2023/02/18 01:20:10 - mmengine - INFO - Epoch(train) [22][1240/1320] lr: 2.0000e-02 eta: 2:38:53 time: 0.2547 data_time: 0.0102 memory: 13708 grad_norm: 4.5209 loss: 2.2015 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.2015 2023/02/18 01:20:15 - mmengine - INFO - Epoch(train) [22][1260/1320] lr: 2.0000e-02 eta: 2:38:48 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 4.3983 loss: 1.9490 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9490 2023/02/18 01:20:20 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:20:20 - mmengine - INFO - Epoch(train) [22][1280/1320] lr: 2.0000e-02 eta: 2:38:43 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.3254 loss: 2.0700 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0700 2023/02/18 01:20:25 - mmengine - INFO - Epoch(train) [22][1300/1320] lr: 2.0000e-02 eta: 2:38:37 time: 0.2548 data_time: 0.0103 memory: 13708 grad_norm: 4.5119 loss: 2.0705 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.0705 2023/02/18 01:20:30 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:20:30 - mmengine - INFO - Epoch(train) [22][1320/1320] lr: 2.0000e-02 eta: 2:38:32 time: 0.2508 data_time: 0.0106 memory: 13708 grad_norm: 4.5477 loss: 1.8784 top1_acc: 0.7273 top5_acc: 0.7273 loss_cls: 1.8784 2023/02/18 01:20:32 - mmengine - INFO - Epoch(val) [22][ 20/194] eta: 0:00:21 time: 0.1232 data_time: 0.0544 memory: 1818 2023/02/18 01:20:34 - mmengine - INFO - Epoch(val) [22][ 40/194] eta: 0:00:16 time: 0.0886 data_time: 0.0185 memory: 1818 2023/02/18 01:20:36 - mmengine - INFO - Epoch(val) [22][ 60/194] eta: 0:00:13 time: 0.0862 data_time: 0.0179 memory: 1818 2023/02/18 01:20:38 - mmengine - INFO - Epoch(val) [22][ 80/194] eta: 0:00:10 time: 0.0853 data_time: 0.0167 memory: 1818 2023/02/18 01:20:39 - mmengine - INFO - Epoch(val) [22][100/194] eta: 0:00:08 time: 0.0907 data_time: 0.0223 memory: 1818 2023/02/18 01:20:41 - mmengine - INFO - Epoch(val) [22][120/194] eta: 0:00:06 time: 0.0853 data_time: 0.0167 memory: 1818 2023/02/18 01:20:43 - mmengine - INFO - Epoch(val) [22][140/194] eta: 0:00:05 time: 0.0958 data_time: 0.0276 memory: 1818 2023/02/18 01:20:45 - mmengine - INFO - Epoch(val) [22][160/194] eta: 0:00:03 time: 0.0823 data_time: 0.0135 memory: 1818 2023/02/18 01:20:46 - mmengine - INFO - Epoch(val) [22][180/194] eta: 0:00:01 time: 0.0839 data_time: 0.0149 memory: 1818 2023/02/18 01:20:48 - mmengine - INFO - Epoch(val) [22][194/194] acc/top1: 0.4628 acc/top5: 0.7552 acc/mean1: 0.3911 2023/02/18 01:20:54 - mmengine - INFO - Epoch(train) [23][ 20/1320] lr: 2.0000e-02 eta: 2:38:28 time: 0.2984 data_time: 0.0456 memory: 13708 grad_norm: 4.4745 loss: 1.9758 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9758 2023/02/18 01:20:59 - mmengine - INFO - Epoch(train) [23][ 40/1320] lr: 2.0000e-02 eta: 2:38:23 time: 0.2549 data_time: 0.0104 memory: 13708 grad_norm: 4.4783 loss: 1.8533 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8533 2023/02/18 01:21:05 - mmengine - INFO - Epoch(train) [23][ 60/1320] lr: 2.0000e-02 eta: 2:38:18 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.5230 loss: 1.9978 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9978 2023/02/18 01:21:10 - mmengine - INFO - Epoch(train) [23][ 80/1320] lr: 2.0000e-02 eta: 2:38:12 time: 0.2550 data_time: 0.0104 memory: 13708 grad_norm: 4.4089 loss: 1.7736 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.7736 2023/02/18 01:21:15 - mmengine - INFO - Epoch(train) [23][ 100/1320] lr: 2.0000e-02 eta: 2:38:07 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.4736 loss: 1.8712 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8712 2023/02/18 01:21:20 - mmengine - INFO - Epoch(train) [23][ 120/1320] lr: 2.0000e-02 eta: 2:38:02 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 4.5231 loss: 2.1293 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.1293 2023/02/18 01:21:25 - mmengine - INFO - Epoch(train) [23][ 140/1320] lr: 2.0000e-02 eta: 2:37:57 time: 0.2548 data_time: 0.0102 memory: 13708 grad_norm: 4.4296 loss: 1.8417 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.8417 2023/02/18 01:21:30 - mmengine - INFO - Epoch(train) [23][ 160/1320] lr: 2.0000e-02 eta: 2:37:52 time: 0.2581 data_time: 0.0136 memory: 13708 grad_norm: 4.6013 loss: 2.0906 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0906 2023/02/18 01:21:35 - mmengine - INFO - Epoch(train) [23][ 180/1320] lr: 2.0000e-02 eta: 2:37:46 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 4.4483 loss: 1.9131 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.9131 2023/02/18 01:21:40 - mmengine - INFO - Epoch(train) [23][ 200/1320] lr: 2.0000e-02 eta: 2:37:41 time: 0.2551 data_time: 0.0110 memory: 13708 grad_norm: 4.5629 loss: 2.0982 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0982 2023/02/18 01:21:45 - mmengine - INFO - Epoch(train) [23][ 220/1320] lr: 2.0000e-02 eta: 2:37:36 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.5943 loss: 1.8082 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8082 2023/02/18 01:21:51 - mmengine - INFO - Epoch(train) [23][ 240/1320] lr: 2.0000e-02 eta: 2:37:31 time: 0.2562 data_time: 0.0116 memory: 13708 grad_norm: 4.4620 loss: 1.6652 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.6652 2023/02/18 01:21:56 - mmengine - INFO - Epoch(train) [23][ 260/1320] lr: 2.0000e-02 eta: 2:37:26 time: 0.2555 data_time: 0.0112 memory: 13708 grad_norm: 4.4566 loss: 1.9003 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9003 2023/02/18 01:22:01 - mmengine - INFO - Epoch(train) [23][ 280/1320] lr: 2.0000e-02 eta: 2:37:20 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.5525 loss: 2.0534 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0534 2023/02/18 01:22:06 - mmengine - INFO - Epoch(train) [23][ 300/1320] lr: 2.0000e-02 eta: 2:37:15 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 4.6076 loss: 1.6439 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.6439 2023/02/18 01:22:11 - mmengine - INFO - Epoch(train) [23][ 320/1320] lr: 2.0000e-02 eta: 2:37:10 time: 0.2555 data_time: 0.0113 memory: 13708 grad_norm: 4.5962 loss: 1.9739 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9739 2023/02/18 01:22:16 - mmengine - INFO - Epoch(train) [23][ 340/1320] lr: 2.0000e-02 eta: 2:37:05 time: 0.2552 data_time: 0.0104 memory: 13708 grad_norm: 4.6715 loss: 1.8788 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8788 2023/02/18 01:22:21 - mmengine - INFO - Epoch(train) [23][ 360/1320] lr: 2.0000e-02 eta: 2:37:00 time: 0.2560 data_time: 0.0112 memory: 13708 grad_norm: 4.5653 loss: 2.0565 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0565 2023/02/18 01:22:26 - mmengine - INFO - Epoch(train) [23][ 380/1320] lr: 2.0000e-02 eta: 2:36:54 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.5024 loss: 1.7547 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.7547 2023/02/18 01:22:31 - mmengine - INFO - Epoch(train) [23][ 400/1320] lr: 2.0000e-02 eta: 2:36:49 time: 0.2556 data_time: 0.0104 memory: 13708 grad_norm: 4.5039 loss: 1.6819 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.6819 2023/02/18 01:22:37 - mmengine - INFO - Epoch(train) [23][ 420/1320] lr: 2.0000e-02 eta: 2:36:44 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.4765 loss: 1.8555 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.8555 2023/02/18 01:22:42 - mmengine - INFO - Epoch(train) [23][ 440/1320] lr: 2.0000e-02 eta: 2:36:39 time: 0.2561 data_time: 0.0112 memory: 13708 grad_norm: 4.3837 loss: 1.7522 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.7522 2023/02/18 01:22:47 - mmengine - INFO - Epoch(train) [23][ 460/1320] lr: 2.0000e-02 eta: 2:36:34 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.5055 loss: 1.8532 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8532 2023/02/18 01:22:52 - mmengine - INFO - Epoch(train) [23][ 480/1320] lr: 2.0000e-02 eta: 2:36:29 time: 0.2559 data_time: 0.0114 memory: 13708 grad_norm: 4.6523 loss: 1.9447 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9447 2023/02/18 01:22:57 - mmengine - INFO - Epoch(train) [23][ 500/1320] lr: 2.0000e-02 eta: 2:36:23 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 4.4560 loss: 2.0880 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0880 2023/02/18 01:23:02 - mmengine - INFO - Epoch(train) [23][ 520/1320] lr: 2.0000e-02 eta: 2:36:18 time: 0.2552 data_time: 0.0103 memory: 13708 grad_norm: 4.3869 loss: 2.0555 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0555 2023/02/18 01:23:07 - mmengine - INFO - Epoch(train) [23][ 540/1320] lr: 2.0000e-02 eta: 2:36:13 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 4.5707 loss: 1.9196 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9196 2023/02/18 01:23:12 - mmengine - INFO - Epoch(train) [23][ 560/1320] lr: 2.0000e-02 eta: 2:36:08 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.4288 loss: 1.9089 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9089 2023/02/18 01:23:17 - mmengine - INFO - Epoch(train) [23][ 580/1320] lr: 2.0000e-02 eta: 2:36:03 time: 0.2550 data_time: 0.0109 memory: 13708 grad_norm: 4.3639 loss: 1.9710 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.9710 2023/02/18 01:23:23 - mmengine - INFO - Epoch(train) [23][ 600/1320] lr: 2.0000e-02 eta: 2:35:57 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 4.4428 loss: 1.8528 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8528 2023/02/18 01:23:28 - mmengine - INFO - Epoch(train) [23][ 620/1320] lr: 2.0000e-02 eta: 2:35:52 time: 0.2546 data_time: 0.0102 memory: 13708 grad_norm: 4.6005 loss: 1.9166 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9166 2023/02/18 01:23:33 - mmengine - INFO - Epoch(train) [23][ 640/1320] lr: 2.0000e-02 eta: 2:35:47 time: 0.2582 data_time: 0.0133 memory: 13708 grad_norm: 4.4761 loss: 2.0653 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0653 2023/02/18 01:23:38 - mmengine - INFO - Epoch(train) [23][ 660/1320] lr: 2.0000e-02 eta: 2:35:42 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.3682 loss: 2.0419 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.0419 2023/02/18 01:23:43 - mmengine - INFO - Epoch(train) [23][ 680/1320] lr: 2.0000e-02 eta: 2:35:37 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.5202 loss: 1.8900 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8900 2023/02/18 01:23:48 - mmengine - INFO - Epoch(train) [23][ 700/1320] lr: 2.0000e-02 eta: 2:35:31 time: 0.2550 data_time: 0.0104 memory: 13708 grad_norm: 4.5787 loss: 1.9217 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9217 2023/02/18 01:23:53 - mmengine - INFO - Epoch(train) [23][ 720/1320] lr: 2.0000e-02 eta: 2:35:26 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.4520 loss: 2.0221 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0221 2023/02/18 01:23:58 - mmengine - INFO - Epoch(train) [23][ 740/1320] lr: 2.0000e-02 eta: 2:35:21 time: 0.2555 data_time: 0.0110 memory: 13708 grad_norm: 4.4952 loss: 1.9701 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.9701 2023/02/18 01:24:03 - mmengine - INFO - Epoch(train) [23][ 760/1320] lr: 2.0000e-02 eta: 2:35:16 time: 0.2546 data_time: 0.0106 memory: 13708 grad_norm: 4.3981 loss: 1.8561 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8561 2023/02/18 01:24:09 - mmengine - INFO - Epoch(train) [23][ 780/1320] lr: 2.0000e-02 eta: 2:35:11 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.4135 loss: 1.9913 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.9913 2023/02/18 01:24:14 - mmengine - INFO - Epoch(train) [23][ 800/1320] lr: 2.0000e-02 eta: 2:35:05 time: 0.2555 data_time: 0.0106 memory: 13708 grad_norm: 4.4490 loss: 2.0355 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.0355 2023/02/18 01:24:19 - mmengine - INFO - Epoch(train) [23][ 820/1320] lr: 2.0000e-02 eta: 2:35:00 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.5627 loss: 2.0207 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.0207 2023/02/18 01:24:24 - mmengine - INFO - Epoch(train) [23][ 840/1320] lr: 2.0000e-02 eta: 2:34:55 time: 0.2556 data_time: 0.0103 memory: 13708 grad_norm: 4.4353 loss: 2.1144 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1144 2023/02/18 01:24:29 - mmengine - INFO - Epoch(train) [23][ 860/1320] lr: 2.0000e-02 eta: 2:34:50 time: 0.2565 data_time: 0.0115 memory: 13708 grad_norm: 4.3297 loss: 1.9635 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.9635 2023/02/18 01:24:34 - mmengine - INFO - Epoch(train) [23][ 880/1320] lr: 2.0000e-02 eta: 2:34:45 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.4013 loss: 2.1037 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.1037 2023/02/18 01:24:39 - mmengine - INFO - Epoch(train) [23][ 900/1320] lr: 2.0000e-02 eta: 2:34:39 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.3351 loss: 1.7379 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.7379 2023/02/18 01:24:44 - mmengine - INFO - Epoch(train) [23][ 920/1320] lr: 2.0000e-02 eta: 2:34:34 time: 0.2551 data_time: 0.0107 memory: 13708 grad_norm: 4.4062 loss: 2.0145 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0145 2023/02/18 01:24:49 - mmengine - INFO - Epoch(train) [23][ 940/1320] lr: 2.0000e-02 eta: 2:34:29 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.4375 loss: 2.0960 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0960 2023/02/18 01:24:55 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:24:55 - mmengine - INFO - Epoch(train) [23][ 960/1320] lr: 2.0000e-02 eta: 2:34:24 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 4.3708 loss: 1.9916 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9916 2023/02/18 01:25:00 - mmengine - INFO - Epoch(train) [23][ 980/1320] lr: 2.0000e-02 eta: 2:34:19 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.4486 loss: 2.0965 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0965 2023/02/18 01:25:05 - mmengine - INFO - Epoch(train) [23][1000/1320] lr: 2.0000e-02 eta: 2:34:13 time: 0.2560 data_time: 0.0107 memory: 13708 grad_norm: 4.3478 loss: 2.0557 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0557 2023/02/18 01:25:10 - mmengine - INFO - Epoch(train) [23][1020/1320] lr: 2.0000e-02 eta: 2:34:08 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 4.3864 loss: 1.8702 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.8702 2023/02/18 01:25:15 - mmengine - INFO - Epoch(train) [23][1040/1320] lr: 2.0000e-02 eta: 2:34:03 time: 0.2547 data_time: 0.0102 memory: 13708 grad_norm: 4.4553 loss: 1.9117 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9117 2023/02/18 01:25:20 - mmengine - INFO - Epoch(train) [23][1060/1320] lr: 2.0000e-02 eta: 2:33:58 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 4.5452 loss: 2.1519 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.1519 2023/02/18 01:25:25 - mmengine - INFO - Epoch(train) [23][1080/1320] lr: 2.0000e-02 eta: 2:33:53 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.4772 loss: 1.9393 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.9393 2023/02/18 01:25:30 - mmengine - INFO - Epoch(train) [23][1100/1320] lr: 2.0000e-02 eta: 2:33:48 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.5140 loss: 1.9298 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9298 2023/02/18 01:25:35 - mmengine - INFO - Epoch(train) [23][1120/1320] lr: 2.0000e-02 eta: 2:33:42 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.4102 loss: 1.9304 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9304 2023/02/18 01:25:41 - mmengine - INFO - Epoch(train) [23][1140/1320] lr: 2.0000e-02 eta: 2:33:37 time: 0.2564 data_time: 0.0105 memory: 13708 grad_norm: 4.4719 loss: 1.9526 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.9526 2023/02/18 01:25:46 - mmengine - INFO - Epoch(train) [23][1160/1320] lr: 2.0000e-02 eta: 2:33:32 time: 0.2555 data_time: 0.0110 memory: 13708 grad_norm: 4.4700 loss: 2.1000 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1000 2023/02/18 01:25:51 - mmengine - INFO - Epoch(train) [23][1180/1320] lr: 2.0000e-02 eta: 2:33:27 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.5246 loss: 1.9737 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9737 2023/02/18 01:25:56 - mmengine - INFO - Epoch(train) [23][1200/1320] lr: 2.0000e-02 eta: 2:33:22 time: 0.2550 data_time: 0.0101 memory: 13708 grad_norm: 4.4513 loss: 1.9442 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9442 2023/02/18 01:26:01 - mmengine - INFO - Epoch(train) [23][1220/1320] lr: 2.0000e-02 eta: 2:33:16 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 4.4875 loss: 2.0013 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0013 2023/02/18 01:26:06 - mmengine - INFO - Epoch(train) [23][1240/1320] lr: 2.0000e-02 eta: 2:33:11 time: 0.2561 data_time: 0.0113 memory: 13708 grad_norm: 4.5591 loss: 2.0131 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0131 2023/02/18 01:26:11 - mmengine - INFO - Epoch(train) [23][1260/1320] lr: 2.0000e-02 eta: 2:33:06 time: 0.2552 data_time: 0.0104 memory: 13708 grad_norm: 4.4356 loss: 1.8847 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8847 2023/02/18 01:26:16 - mmengine - INFO - Epoch(train) [23][1280/1320] lr: 2.0000e-02 eta: 2:33:01 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 4.4154 loss: 2.1835 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1835 2023/02/18 01:26:22 - mmengine - INFO - Epoch(train) [23][1300/1320] lr: 2.0000e-02 eta: 2:32:56 time: 0.2565 data_time: 0.0120 memory: 13708 grad_norm: 4.4257 loss: 1.8381 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8381 2023/02/18 01:26:27 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:26:27 - mmengine - INFO - Epoch(train) [23][1320/1320] lr: 2.0000e-02 eta: 2:32:50 time: 0.2509 data_time: 0.0107 memory: 13708 grad_norm: 4.5894 loss: 1.9242 top1_acc: 0.4545 top5_acc: 0.8182 loss_cls: 1.9242 2023/02/18 01:26:29 - mmengine - INFO - Epoch(val) [23][ 20/194] eta: 0:00:21 time: 0.1208 data_time: 0.0530 memory: 1818 2023/02/18 01:26:31 - mmengine - INFO - Epoch(val) [23][ 40/194] eta: 0:00:15 time: 0.0849 data_time: 0.0172 memory: 1818 2023/02/18 01:26:32 - mmengine - INFO - Epoch(val) [23][ 60/194] eta: 0:00:13 time: 0.0882 data_time: 0.0205 memory: 1818 2023/02/18 01:26:34 - mmengine - INFO - Epoch(val) [23][ 80/194] eta: 0:00:10 time: 0.0848 data_time: 0.0145 memory: 1818 2023/02/18 01:26:36 - mmengine - INFO - Epoch(val) [23][100/194] eta: 0:00:08 time: 0.0883 data_time: 0.0198 memory: 1818 2023/02/18 01:26:38 - mmengine - INFO - Epoch(val) [23][120/194] eta: 0:00:06 time: 0.0861 data_time: 0.0178 memory: 1818 2023/02/18 01:26:39 - mmengine - INFO - Epoch(val) [23][140/194] eta: 0:00:04 time: 0.0901 data_time: 0.0216 memory: 1818 2023/02/18 01:26:41 - mmengine - INFO - Epoch(val) [23][160/194] eta: 0:00:03 time: 0.0810 data_time: 0.0128 memory: 1818 2023/02/18 01:26:43 - mmengine - INFO - Epoch(val) [23][180/194] eta: 0:00:01 time: 0.0896 data_time: 0.0207 memory: 1818 2023/02/18 01:26:45 - mmengine - INFO - Epoch(val) [23][194/194] acc/top1: 0.4498 acc/top5: 0.7452 acc/mean1: 0.3863 2023/02/18 01:26:51 - mmengine - INFO - Epoch(train) [24][ 20/1320] lr: 2.0000e-02 eta: 2:32:46 time: 0.3019 data_time: 0.0456 memory: 13708 grad_norm: 4.3788 loss: 1.9008 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.9008 2023/02/18 01:26:56 - mmengine - INFO - Epoch(train) [24][ 40/1320] lr: 2.0000e-02 eta: 2:32:41 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 4.3538 loss: 1.9818 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 1.9818 2023/02/18 01:27:01 - mmengine - INFO - Epoch(train) [24][ 60/1320] lr: 2.0000e-02 eta: 2:32:36 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.4256 loss: 1.8604 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.8604 2023/02/18 01:27:07 - mmengine - INFO - Epoch(train) [24][ 80/1320] lr: 2.0000e-02 eta: 2:32:31 time: 0.2567 data_time: 0.0125 memory: 13708 grad_norm: 4.5290 loss: 1.8340 top1_acc: 0.1875 top5_acc: 0.8125 loss_cls: 1.8340 2023/02/18 01:27:12 - mmengine - INFO - Epoch(train) [24][ 100/1320] lr: 2.0000e-02 eta: 2:32:25 time: 0.2553 data_time: 0.0112 memory: 13708 grad_norm: 4.4761 loss: 1.9475 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9475 2023/02/18 01:27:17 - mmengine - INFO - Epoch(train) [24][ 120/1320] lr: 2.0000e-02 eta: 2:32:20 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.4314 loss: 1.7314 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.7314 2023/02/18 01:27:22 - mmengine - INFO - Epoch(train) [24][ 140/1320] lr: 2.0000e-02 eta: 2:32:15 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.6331 loss: 1.9657 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9657 2023/02/18 01:27:27 - mmengine - INFO - Epoch(train) [24][ 160/1320] lr: 2.0000e-02 eta: 2:32:10 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.5302 loss: 2.0329 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0329 2023/02/18 01:27:32 - mmengine - INFO - Epoch(train) [24][ 180/1320] lr: 2.0000e-02 eta: 2:32:05 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 4.5155 loss: 1.9970 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 1.9970 2023/02/18 01:27:37 - mmengine - INFO - Epoch(train) [24][ 200/1320] lr: 2.0000e-02 eta: 2:32:00 time: 0.2557 data_time: 0.0112 memory: 13708 grad_norm: 4.4676 loss: 2.0944 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0944 2023/02/18 01:27:42 - mmengine - INFO - Epoch(train) [24][ 220/1320] lr: 2.0000e-02 eta: 2:31:54 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.5270 loss: 1.7845 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.7845 2023/02/18 01:27:47 - mmengine - INFO - Epoch(train) [24][ 240/1320] lr: 2.0000e-02 eta: 2:31:49 time: 0.2550 data_time: 0.0110 memory: 13708 grad_norm: 4.4382 loss: 1.9101 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9101 2023/02/18 01:27:52 - mmengine - INFO - Epoch(train) [24][ 260/1320] lr: 2.0000e-02 eta: 2:31:44 time: 0.2545 data_time: 0.0102 memory: 13708 grad_norm: 4.4033 loss: 1.8640 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.8640 2023/02/18 01:27:58 - mmengine - INFO - Epoch(train) [24][ 280/1320] lr: 2.0000e-02 eta: 2:31:39 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.6468 loss: 1.8299 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.8299 2023/02/18 01:28:03 - mmengine - INFO - Epoch(train) [24][ 300/1320] lr: 2.0000e-02 eta: 2:31:34 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 4.5146 loss: 1.9195 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 1.9195 2023/02/18 01:28:08 - mmengine - INFO - Epoch(train) [24][ 320/1320] lr: 2.0000e-02 eta: 2:31:28 time: 0.2546 data_time: 0.0101 memory: 13708 grad_norm: 4.5492 loss: 1.9120 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.9120 2023/02/18 01:28:13 - mmengine - INFO - Epoch(train) [24][ 340/1320] lr: 2.0000e-02 eta: 2:31:23 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.5011 loss: 1.8931 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.8931 2023/02/18 01:28:18 - mmengine - INFO - Epoch(train) [24][ 360/1320] lr: 2.0000e-02 eta: 2:31:18 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 4.4618 loss: 1.7449 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.7449 2023/02/18 01:28:23 - mmengine - INFO - Epoch(train) [24][ 380/1320] lr: 2.0000e-02 eta: 2:31:13 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.4719 loss: 1.9230 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9230 2023/02/18 01:28:28 - mmengine - INFO - Epoch(train) [24][ 400/1320] lr: 2.0000e-02 eta: 2:31:08 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.5403 loss: 1.8791 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8791 2023/02/18 01:28:33 - mmengine - INFO - Epoch(train) [24][ 420/1320] lr: 2.0000e-02 eta: 2:31:02 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 4.4314 loss: 1.8389 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8389 2023/02/18 01:28:38 - mmengine - INFO - Epoch(train) [24][ 440/1320] lr: 2.0000e-02 eta: 2:30:57 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 4.5074 loss: 1.9344 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.9344 2023/02/18 01:28:44 - mmengine - INFO - Epoch(train) [24][ 460/1320] lr: 2.0000e-02 eta: 2:30:52 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.6069 loss: 2.0386 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0386 2023/02/18 01:28:49 - mmengine - INFO - Epoch(train) [24][ 480/1320] lr: 2.0000e-02 eta: 2:30:47 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.4229 loss: 1.8178 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8178 2023/02/18 01:28:54 - mmengine - INFO - Epoch(train) [24][ 500/1320] lr: 2.0000e-02 eta: 2:30:42 time: 0.2555 data_time: 0.0111 memory: 13708 grad_norm: 4.6014 loss: 2.0716 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0716 2023/02/18 01:28:59 - mmengine - INFO - Epoch(train) [24][ 520/1320] lr: 2.0000e-02 eta: 2:30:36 time: 0.2548 data_time: 0.0102 memory: 13708 grad_norm: 4.4790 loss: 1.8706 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8706 2023/02/18 01:29:04 - mmengine - INFO - Epoch(train) [24][ 540/1320] lr: 2.0000e-02 eta: 2:30:31 time: 0.2563 data_time: 0.0114 memory: 13708 grad_norm: 4.5258 loss: 1.8725 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8725 2023/02/18 01:29:09 - mmengine - INFO - Epoch(train) [24][ 560/1320] lr: 2.0000e-02 eta: 2:30:26 time: 0.2555 data_time: 0.0111 memory: 13708 grad_norm: 4.4978 loss: 1.9883 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9883 2023/02/18 01:29:14 - mmengine - INFO - Epoch(train) [24][ 580/1320] lr: 2.0000e-02 eta: 2:30:21 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.4162 loss: 1.9607 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9607 2023/02/18 01:29:19 - mmengine - INFO - Epoch(train) [24][ 600/1320] lr: 2.0000e-02 eta: 2:30:16 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 4.4844 loss: 1.8066 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8066 2023/02/18 01:29:24 - mmengine - INFO - Epoch(train) [24][ 620/1320] lr: 2.0000e-02 eta: 2:30:10 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.4846 loss: 1.9282 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.9282 2023/02/18 01:29:30 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:29:30 - mmengine - INFO - Epoch(train) [24][ 640/1320] lr: 2.0000e-02 eta: 2:30:05 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 4.3610 loss: 1.9235 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.9235 2023/02/18 01:29:35 - mmengine - INFO - Epoch(train) [24][ 660/1320] lr: 2.0000e-02 eta: 2:30:00 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.4326 loss: 1.8943 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.8943 2023/02/18 01:29:40 - mmengine - INFO - Epoch(train) [24][ 680/1320] lr: 2.0000e-02 eta: 2:29:55 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.4827 loss: 1.8156 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.8156 2023/02/18 01:29:45 - mmengine - INFO - Epoch(train) [24][ 700/1320] lr: 2.0000e-02 eta: 2:29:50 time: 0.2552 data_time: 0.0112 memory: 13708 grad_norm: 4.3580 loss: 2.0951 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0951 2023/02/18 01:29:50 - mmengine - INFO - Epoch(train) [24][ 720/1320] lr: 2.0000e-02 eta: 2:29:45 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 4.5232 loss: 2.0780 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0780 2023/02/18 01:29:55 - mmengine - INFO - Epoch(train) [24][ 740/1320] lr: 2.0000e-02 eta: 2:29:39 time: 0.2563 data_time: 0.0120 memory: 13708 grad_norm: 4.5132 loss: 1.6367 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.6367 2023/02/18 01:30:00 - mmengine - INFO - Epoch(train) [24][ 760/1320] lr: 2.0000e-02 eta: 2:29:34 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 4.5615 loss: 1.9462 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.9462 2023/02/18 01:30:05 - mmengine - INFO - Epoch(train) [24][ 780/1320] lr: 2.0000e-02 eta: 2:29:29 time: 0.2560 data_time: 0.0102 memory: 13708 grad_norm: 4.5453 loss: 1.8901 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8901 2023/02/18 01:30:10 - mmengine - INFO - Epoch(train) [24][ 800/1320] lr: 2.0000e-02 eta: 2:29:24 time: 0.2558 data_time: 0.0111 memory: 13708 grad_norm: 4.5540 loss: 2.0772 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 2.0772 2023/02/18 01:30:16 - mmengine - INFO - Epoch(train) [24][ 820/1320] lr: 2.0000e-02 eta: 2:29:19 time: 0.2555 data_time: 0.0112 memory: 13708 grad_norm: 4.4778 loss: 1.9891 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9891 2023/02/18 01:30:21 - mmengine - INFO - Epoch(train) [24][ 840/1320] lr: 2.0000e-02 eta: 2:29:13 time: 0.2546 data_time: 0.0106 memory: 13708 grad_norm: 4.5088 loss: 2.0996 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0996 2023/02/18 01:30:26 - mmengine - INFO - Epoch(train) [24][ 860/1320] lr: 2.0000e-02 eta: 2:29:08 time: 0.2550 data_time: 0.0110 memory: 13708 grad_norm: 4.4721 loss: 2.0481 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0481 2023/02/18 01:30:31 - mmengine - INFO - Epoch(train) [24][ 880/1320] lr: 2.0000e-02 eta: 2:29:03 time: 0.2562 data_time: 0.0116 memory: 13708 grad_norm: 4.3537 loss: 1.9163 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.9163 2023/02/18 01:30:36 - mmengine - INFO - Epoch(train) [24][ 900/1320] lr: 2.0000e-02 eta: 2:28:58 time: 0.2585 data_time: 0.0142 memory: 13708 grad_norm: 4.3881 loss: 1.9163 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 1.9163 2023/02/18 01:30:41 - mmengine - INFO - Epoch(train) [24][ 920/1320] lr: 2.0000e-02 eta: 2:28:53 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.4837 loss: 2.0793 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.0793 2023/02/18 01:30:46 - mmengine - INFO - Epoch(train) [24][ 940/1320] lr: 2.0000e-02 eta: 2:28:48 time: 0.2545 data_time: 0.0105 memory: 13708 grad_norm: 4.3519 loss: 2.0858 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0858 2023/02/18 01:30:51 - mmengine - INFO - Epoch(train) [24][ 960/1320] lr: 2.0000e-02 eta: 2:28:42 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.4274 loss: 1.8005 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.8005 2023/02/18 01:30:57 - mmengine - INFO - Epoch(train) [24][ 980/1320] lr: 2.0000e-02 eta: 2:28:37 time: 0.2564 data_time: 0.0105 memory: 13708 grad_norm: 4.4237 loss: 1.9483 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9483 2023/02/18 01:31:02 - mmengine - INFO - Epoch(train) [24][1000/1320] lr: 2.0000e-02 eta: 2:28:32 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 4.4051 loss: 1.9126 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.9126 2023/02/18 01:31:07 - mmengine - INFO - Epoch(train) [24][1020/1320] lr: 2.0000e-02 eta: 2:28:27 time: 0.2562 data_time: 0.0116 memory: 13708 grad_norm: 4.4581 loss: 1.8906 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.8906 2023/02/18 01:31:12 - mmengine - INFO - Epoch(train) [24][1040/1320] lr: 2.0000e-02 eta: 2:28:22 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 4.5184 loss: 1.8996 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8996 2023/02/18 01:31:17 - mmengine - INFO - Epoch(train) [24][1060/1320] lr: 2.0000e-02 eta: 2:28:16 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 4.4429 loss: 2.2155 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.2155 2023/02/18 01:31:22 - mmengine - INFO - Epoch(train) [24][1080/1320] lr: 2.0000e-02 eta: 2:28:11 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.4653 loss: 1.8986 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.8986 2023/02/18 01:31:27 - mmengine - INFO - Epoch(train) [24][1100/1320] lr: 2.0000e-02 eta: 2:28:06 time: 0.2560 data_time: 0.0105 memory: 13708 grad_norm: 4.4069 loss: 1.9779 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9779 2023/02/18 01:31:32 - mmengine - INFO - Epoch(train) [24][1120/1320] lr: 2.0000e-02 eta: 2:28:01 time: 0.2553 data_time: 0.0103 memory: 13708 grad_norm: 4.4818 loss: 1.9139 top1_acc: 0.2500 top5_acc: 0.8750 loss_cls: 1.9139 2023/02/18 01:31:37 - mmengine - INFO - Epoch(train) [24][1140/1320] lr: 2.0000e-02 eta: 2:27:56 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.4156 loss: 2.0256 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0256 2023/02/18 01:31:43 - mmengine - INFO - Epoch(train) [24][1160/1320] lr: 2.0000e-02 eta: 2:27:51 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 4.4649 loss: 2.1413 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.1413 2023/02/18 01:31:48 - mmengine - INFO - Epoch(train) [24][1180/1320] lr: 2.0000e-02 eta: 2:27:45 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 4.5002 loss: 1.7991 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.7991 2023/02/18 01:31:53 - mmengine - INFO - Epoch(train) [24][1200/1320] lr: 2.0000e-02 eta: 2:27:40 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 4.5468 loss: 1.9548 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9548 2023/02/18 01:31:58 - mmengine - INFO - Epoch(train) [24][1220/1320] lr: 2.0000e-02 eta: 2:27:35 time: 0.2547 data_time: 0.0103 memory: 13708 grad_norm: 4.5812 loss: 2.0588 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 2.0588 2023/02/18 01:32:03 - mmengine - INFO - Epoch(train) [24][1240/1320] lr: 2.0000e-02 eta: 2:27:30 time: 0.2555 data_time: 0.0106 memory: 13708 grad_norm: 4.5872 loss: 1.6976 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.6976 2023/02/18 01:32:08 - mmengine - INFO - Epoch(train) [24][1260/1320] lr: 2.0000e-02 eta: 2:27:25 time: 0.2560 data_time: 0.0111 memory: 13708 grad_norm: 4.3918 loss: 1.8947 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8947 2023/02/18 01:32:13 - mmengine - INFO - Epoch(train) [24][1280/1320] lr: 2.0000e-02 eta: 2:27:19 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 4.4610 loss: 1.8293 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8293 2023/02/18 01:32:18 - mmengine - INFO - Epoch(train) [24][1300/1320] lr: 2.0000e-02 eta: 2:27:14 time: 0.2570 data_time: 0.0125 memory: 13708 grad_norm: 4.4686 loss: 1.8979 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8979 2023/02/18 01:32:23 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:32:23 - mmengine - INFO - Epoch(train) [24][1320/1320] lr: 2.0000e-02 eta: 2:27:09 time: 0.2513 data_time: 0.0102 memory: 13708 grad_norm: 4.3661 loss: 1.8485 top1_acc: 0.5455 top5_acc: 0.7273 loss_cls: 1.8485 2023/02/18 01:32:23 - mmengine - INFO - Saving checkpoint at 24 epochs 2023/02/18 01:32:27 - mmengine - INFO - Epoch(val) [24][ 20/194] eta: 0:00:22 time: 0.1291 data_time: 0.0594 memory: 1818 2023/02/18 01:32:29 - mmengine - INFO - Epoch(val) [24][ 40/194] eta: 0:00:16 time: 0.0866 data_time: 0.0184 memory: 1818 2023/02/18 01:32:31 - mmengine - INFO - Epoch(val) [24][ 60/194] eta: 0:00:13 time: 0.0882 data_time: 0.0196 memory: 1818 2023/02/18 01:32:33 - mmengine - INFO - Epoch(val) [24][ 80/194] eta: 0:00:11 time: 0.0919 data_time: 0.0218 memory: 1818 2023/02/18 01:32:34 - mmengine - INFO - Epoch(val) [24][100/194] eta: 0:00:09 time: 0.0880 data_time: 0.0195 memory: 1818 2023/02/18 01:32:36 - mmengine - INFO - Epoch(val) [24][120/194] eta: 0:00:07 time: 0.0875 data_time: 0.0183 memory: 1818 2023/02/18 01:32:38 - mmengine - INFO - Epoch(val) [24][140/194] eta: 0:00:05 time: 0.0911 data_time: 0.0223 memory: 1818 2023/02/18 01:32:40 - mmengine - INFO - Epoch(val) [24][160/194] eta: 0:00:03 time: 0.0817 data_time: 0.0129 memory: 1818 2023/02/18 01:32:41 - mmengine - INFO - Epoch(val) [24][180/194] eta: 0:00:01 time: 0.0819 data_time: 0.0130 memory: 1818 2023/02/18 01:32:43 - mmengine - INFO - Epoch(val) [24][194/194] acc/top1: 0.4662 acc/top5: 0.7575 acc/mean1: 0.3881 2023/02/18 01:32:49 - mmengine - INFO - Epoch(train) [25][ 20/1320] lr: 2.0000e-02 eta: 2:27:05 time: 0.3013 data_time: 0.0423 memory: 13708 grad_norm: 4.4302 loss: 1.9476 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9476 2023/02/18 01:32:54 - mmengine - INFO - Epoch(train) [25][ 40/1320] lr: 2.0000e-02 eta: 2:27:00 time: 0.2585 data_time: 0.0133 memory: 13708 grad_norm: 4.4732 loss: 1.8786 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.8786 2023/02/18 01:32:59 - mmengine - INFO - Epoch(train) [25][ 60/1320] lr: 2.0000e-02 eta: 2:26:55 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.5245 loss: 2.0527 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0527 2023/02/18 01:33:04 - mmengine - INFO - Epoch(train) [25][ 80/1320] lr: 2.0000e-02 eta: 2:26:49 time: 0.2543 data_time: 0.0104 memory: 13708 grad_norm: 4.4218 loss: 1.9289 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9289 2023/02/18 01:33:09 - mmengine - INFO - Epoch(train) [25][ 100/1320] lr: 2.0000e-02 eta: 2:26:44 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.4827 loss: 1.8833 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8833 2023/02/18 01:33:14 - mmengine - INFO - Epoch(train) [25][ 120/1320] lr: 2.0000e-02 eta: 2:26:39 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 4.5555 loss: 1.9603 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9603 2023/02/18 01:33:20 - mmengine - INFO - Epoch(train) [25][ 140/1320] lr: 2.0000e-02 eta: 2:26:34 time: 0.2554 data_time: 0.0112 memory: 13708 grad_norm: 4.4603 loss: 2.0724 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0724 2023/02/18 01:33:25 - mmengine - INFO - Epoch(train) [25][ 160/1320] lr: 2.0000e-02 eta: 2:26:29 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.4146 loss: 1.8849 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.8849 2023/02/18 01:33:30 - mmengine - INFO - Epoch(train) [25][ 180/1320] lr: 2.0000e-02 eta: 2:26:23 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 4.5349 loss: 1.8231 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8231 2023/02/18 01:33:35 - mmengine - INFO - Epoch(train) [25][ 200/1320] lr: 2.0000e-02 eta: 2:26:18 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.5627 loss: 2.0367 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0367 2023/02/18 01:33:40 - mmengine - INFO - Epoch(train) [25][ 220/1320] lr: 2.0000e-02 eta: 2:26:13 time: 0.2545 data_time: 0.0104 memory: 13708 grad_norm: 4.5930 loss: 1.9648 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9648 2023/02/18 01:33:45 - mmengine - INFO - Epoch(train) [25][ 240/1320] lr: 2.0000e-02 eta: 2:26:08 time: 0.2555 data_time: 0.0111 memory: 13708 grad_norm: 4.4912 loss: 2.0175 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0175 2023/02/18 01:33:50 - mmengine - INFO - Epoch(train) [25][ 260/1320] lr: 2.0000e-02 eta: 2:26:03 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.3997 loss: 2.1948 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.1948 2023/02/18 01:33:55 - mmengine - INFO - Epoch(train) [25][ 280/1320] lr: 2.0000e-02 eta: 2:25:57 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.5690 loss: 1.9448 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9448 2023/02/18 01:34:00 - mmengine - INFO - Epoch(train) [25][ 300/1320] lr: 2.0000e-02 eta: 2:25:52 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.5313 loss: 1.7996 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.7996 2023/02/18 01:34:06 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:34:06 - mmengine - INFO - Epoch(train) [25][ 320/1320] lr: 2.0000e-02 eta: 2:25:47 time: 0.2565 data_time: 0.0102 memory: 13708 grad_norm: 4.5068 loss: 1.8182 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8182 2023/02/18 01:34:11 - mmengine - INFO - Epoch(train) [25][ 340/1320] lr: 2.0000e-02 eta: 2:25:42 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.5537 loss: 2.0104 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.0104 2023/02/18 01:34:16 - mmengine - INFO - Epoch(train) [25][ 360/1320] lr: 2.0000e-02 eta: 2:25:37 time: 0.2548 data_time: 0.0107 memory: 13708 grad_norm: 4.5049 loss: 1.9746 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9746 2023/02/18 01:34:21 - mmengine - INFO - Epoch(train) [25][ 380/1320] lr: 2.0000e-02 eta: 2:25:31 time: 0.2548 data_time: 0.0103 memory: 13708 grad_norm: 4.5115 loss: 1.9614 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9614 2023/02/18 01:34:26 - mmengine - INFO - Epoch(train) [25][ 400/1320] lr: 2.0000e-02 eta: 2:25:26 time: 0.2554 data_time: 0.0111 memory: 13708 grad_norm: 4.4442 loss: 2.1037 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.1037 2023/02/18 01:34:31 - mmengine - INFO - Epoch(train) [25][ 420/1320] lr: 2.0000e-02 eta: 2:25:21 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.4577 loss: 1.9881 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9881 2023/02/18 01:34:36 - mmengine - INFO - Epoch(train) [25][ 440/1320] lr: 2.0000e-02 eta: 2:25:16 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 4.3911 loss: 2.0945 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 2.0945 2023/02/18 01:34:41 - mmengine - INFO - Epoch(train) [25][ 460/1320] lr: 2.0000e-02 eta: 2:25:11 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 4.4142 loss: 1.9458 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9458 2023/02/18 01:34:46 - mmengine - INFO - Epoch(train) [25][ 480/1320] lr: 2.0000e-02 eta: 2:25:06 time: 0.2549 data_time: 0.0103 memory: 13708 grad_norm: 4.4068 loss: 2.1026 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.1026 2023/02/18 01:34:51 - mmengine - INFO - Epoch(train) [25][ 500/1320] lr: 2.0000e-02 eta: 2:25:00 time: 0.2561 data_time: 0.0113 memory: 13708 grad_norm: 4.4743 loss: 1.8836 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.8836 2023/02/18 01:34:57 - mmengine - INFO - Epoch(train) [25][ 520/1320] lr: 2.0000e-02 eta: 2:24:55 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.5358 loss: 1.7850 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.7850 2023/02/18 01:35:02 - mmengine - INFO - Epoch(train) [25][ 540/1320] lr: 2.0000e-02 eta: 2:24:50 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.5306 loss: 1.8262 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.8262 2023/02/18 01:35:07 - mmengine - INFO - Epoch(train) [25][ 560/1320] lr: 2.0000e-02 eta: 2:24:45 time: 0.2559 data_time: 0.0106 memory: 13708 grad_norm: 4.5241 loss: 1.8903 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.8903 2023/02/18 01:35:12 - mmengine - INFO - Epoch(train) [25][ 580/1320] lr: 2.0000e-02 eta: 2:24:40 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.4157 loss: 2.0091 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0091 2023/02/18 01:35:17 - mmengine - INFO - Epoch(train) [25][ 600/1320] lr: 2.0000e-02 eta: 2:24:34 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.4760 loss: 1.9216 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9216 2023/02/18 01:35:22 - mmengine - INFO - Epoch(train) [25][ 620/1320] lr: 2.0000e-02 eta: 2:24:29 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 4.5139 loss: 2.0174 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0174 2023/02/18 01:35:27 - mmengine - INFO - Epoch(train) [25][ 640/1320] lr: 2.0000e-02 eta: 2:24:24 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.5643 loss: 1.8622 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8622 2023/02/18 01:35:32 - mmengine - INFO - Epoch(train) [25][ 660/1320] lr: 2.0000e-02 eta: 2:24:19 time: 0.2555 data_time: 0.0114 memory: 13708 grad_norm: 4.5826 loss: 2.0843 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0843 2023/02/18 01:35:37 - mmengine - INFO - Epoch(train) [25][ 680/1320] lr: 2.0000e-02 eta: 2:24:14 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.7445 loss: 1.9747 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 1.9747 2023/02/18 01:35:43 - mmengine - INFO - Epoch(train) [25][ 700/1320] lr: 2.0000e-02 eta: 2:24:08 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.4416 loss: 1.9738 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9738 2023/02/18 01:35:48 - mmengine - INFO - Epoch(train) [25][ 720/1320] lr: 2.0000e-02 eta: 2:24:03 time: 0.2558 data_time: 0.0111 memory: 13708 grad_norm: 4.4860 loss: 1.8606 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8606 2023/02/18 01:35:53 - mmengine - INFO - Epoch(train) [25][ 740/1320] lr: 2.0000e-02 eta: 2:23:58 time: 0.2555 data_time: 0.0106 memory: 13708 grad_norm: 4.5249 loss: 2.0656 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.0656 2023/02/18 01:35:58 - mmengine - INFO - Epoch(train) [25][ 760/1320] lr: 2.0000e-02 eta: 2:23:53 time: 0.2567 data_time: 0.0124 memory: 13708 grad_norm: 4.2786 loss: 1.8315 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.8315 2023/02/18 01:36:03 - mmengine - INFO - Epoch(train) [25][ 780/1320] lr: 2.0000e-02 eta: 2:23:48 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.3109 loss: 1.9416 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9416 2023/02/18 01:36:08 - mmengine - INFO - Epoch(train) [25][ 800/1320] lr: 2.0000e-02 eta: 2:23:43 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.5070 loss: 1.8527 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.8527 2023/02/18 01:36:13 - mmengine - INFO - Epoch(train) [25][ 820/1320] lr: 2.0000e-02 eta: 2:23:37 time: 0.2561 data_time: 0.0114 memory: 13708 grad_norm: 4.5937 loss: 1.6264 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.6264 2023/02/18 01:36:18 - mmengine - INFO - Epoch(train) [25][ 840/1320] lr: 2.0000e-02 eta: 2:23:32 time: 0.2565 data_time: 0.0119 memory: 13708 grad_norm: 4.5692 loss: 1.9144 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 1.9144 2023/02/18 01:36:24 - mmengine - INFO - Epoch(train) [25][ 860/1320] lr: 2.0000e-02 eta: 2:23:27 time: 0.2557 data_time: 0.0102 memory: 13708 grad_norm: 4.4205 loss: 2.0919 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0919 2023/02/18 01:36:29 - mmengine - INFO - Epoch(train) [25][ 880/1320] lr: 2.0000e-02 eta: 2:23:22 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.4654 loss: 1.9277 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9277 2023/02/18 01:36:34 - mmengine - INFO - Epoch(train) [25][ 900/1320] lr: 2.0000e-02 eta: 2:23:17 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.5227 loss: 2.0092 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 2.0092 2023/02/18 01:36:39 - mmengine - INFO - Epoch(train) [25][ 920/1320] lr: 2.0000e-02 eta: 2:23:12 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.5661 loss: 1.9232 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9232 2023/02/18 01:36:44 - mmengine - INFO - Epoch(train) [25][ 940/1320] lr: 2.0000e-02 eta: 2:23:06 time: 0.2575 data_time: 0.0125 memory: 13708 grad_norm: 4.4692 loss: 2.0414 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0414 2023/02/18 01:36:49 - mmengine - INFO - Epoch(train) [25][ 960/1320] lr: 2.0000e-02 eta: 2:23:01 time: 0.2547 data_time: 0.0103 memory: 13708 grad_norm: 4.5429 loss: 2.0717 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0717 2023/02/18 01:36:54 - mmengine - INFO - Epoch(train) [25][ 980/1320] lr: 2.0000e-02 eta: 2:22:56 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 4.4113 loss: 2.0238 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0238 2023/02/18 01:36:59 - mmengine - INFO - Epoch(train) [25][1000/1320] lr: 2.0000e-02 eta: 2:22:51 time: 0.2560 data_time: 0.0114 memory: 13708 grad_norm: 4.4823 loss: 1.7725 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.7725 2023/02/18 01:37:04 - mmengine - INFO - Epoch(train) [25][1020/1320] lr: 2.0000e-02 eta: 2:22:46 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 4.4177 loss: 1.8004 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.8004 2023/02/18 01:37:10 - mmengine - INFO - Epoch(train) [25][1040/1320] lr: 2.0000e-02 eta: 2:22:41 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.5953 loss: 2.0038 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0038 2023/02/18 01:37:15 - mmengine - INFO - Epoch(train) [25][1060/1320] lr: 2.0000e-02 eta: 2:22:35 time: 0.2557 data_time: 0.0104 memory: 13708 grad_norm: 4.6301 loss: 1.8969 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8969 2023/02/18 01:37:20 - mmengine - INFO - Epoch(train) [25][1080/1320] lr: 2.0000e-02 eta: 2:22:30 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.3156 loss: 2.0096 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0096 2023/02/18 01:37:25 - mmengine - INFO - Epoch(train) [25][1100/1320] lr: 2.0000e-02 eta: 2:22:25 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.5001 loss: 1.8753 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8753 2023/02/18 01:37:30 - mmengine - INFO - Epoch(train) [25][1120/1320] lr: 2.0000e-02 eta: 2:22:20 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.4056 loss: 1.9648 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9648 2023/02/18 01:37:35 - mmengine - INFO - Epoch(train) [25][1140/1320] lr: 2.0000e-02 eta: 2:22:15 time: 0.2578 data_time: 0.0130 memory: 13708 grad_norm: 4.5022 loss: 1.9244 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9244 2023/02/18 01:37:40 - mmengine - INFO - Epoch(train) [25][1160/1320] lr: 2.0000e-02 eta: 2:22:09 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.5459 loss: 2.0953 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0953 2023/02/18 01:37:45 - mmengine - INFO - Epoch(train) [25][1180/1320] lr: 2.0000e-02 eta: 2:22:04 time: 0.2555 data_time: 0.0106 memory: 13708 grad_norm: 4.3989 loss: 2.0115 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0115 2023/02/18 01:37:51 - mmengine - INFO - Epoch(train) [25][1200/1320] lr: 2.0000e-02 eta: 2:21:59 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 4.4576 loss: 1.8982 top1_acc: 0.2500 top5_acc: 0.8125 loss_cls: 1.8982 2023/02/18 01:37:56 - mmengine - INFO - Epoch(train) [25][1220/1320] lr: 2.0000e-02 eta: 2:21:54 time: 0.2553 data_time: 0.0103 memory: 13708 grad_norm: 4.4559 loss: 2.1108 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1108 2023/02/18 01:38:01 - mmengine - INFO - Epoch(train) [25][1240/1320] lr: 2.0000e-02 eta: 2:21:49 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.4359 loss: 1.9365 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.9365 2023/02/18 01:38:06 - mmengine - INFO - Epoch(train) [25][1260/1320] lr: 2.0000e-02 eta: 2:21:44 time: 0.2557 data_time: 0.0112 memory: 13708 grad_norm: 4.3225 loss: 1.8458 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8458 2023/02/18 01:38:11 - mmengine - INFO - Epoch(train) [25][1280/1320] lr: 2.0000e-02 eta: 2:21:38 time: 0.2550 data_time: 0.0101 memory: 13708 grad_norm: 4.4742 loss: 2.0669 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0669 2023/02/18 01:38:16 - mmengine - INFO - Epoch(train) [25][1300/1320] lr: 2.0000e-02 eta: 2:21:33 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 4.3786 loss: 1.8816 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8816 2023/02/18 01:38:21 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:38:21 - mmengine - INFO - Epoch(train) [25][1320/1320] lr: 2.0000e-02 eta: 2:21:28 time: 0.2512 data_time: 0.0104 memory: 13708 grad_norm: 4.4801 loss: 1.7880 top1_acc: 0.7273 top5_acc: 0.9091 loss_cls: 1.7880 2023/02/18 01:38:24 - mmengine - INFO - Epoch(val) [25][ 20/194] eta: 0:00:21 time: 0.1255 data_time: 0.0549 memory: 1818 2023/02/18 01:38:25 - mmengine - INFO - Epoch(val) [25][ 40/194] eta: 0:00:16 time: 0.0881 data_time: 0.0198 memory: 1818 2023/02/18 01:38:27 - mmengine - INFO - Epoch(val) [25][ 60/194] eta: 0:00:13 time: 0.0904 data_time: 0.0221 memory: 1818 2023/02/18 01:38:29 - mmengine - INFO - Epoch(val) [25][ 80/194] eta: 0:00:10 time: 0.0810 data_time: 0.0126 memory: 1818 2023/02/18 01:38:31 - mmengine - INFO - Epoch(val) [25][100/194] eta: 0:00:08 time: 0.0861 data_time: 0.0186 memory: 1818 2023/02/18 01:38:32 - mmengine - INFO - Epoch(val) [25][120/194] eta: 0:00:06 time: 0.0844 data_time: 0.0168 memory: 1818 2023/02/18 01:38:34 - mmengine - INFO - Epoch(val) [25][140/194] eta: 0:00:05 time: 0.0935 data_time: 0.0231 memory: 1818 2023/02/18 01:38:36 - mmengine - INFO - Epoch(val) [25][160/194] eta: 0:00:03 time: 0.0813 data_time: 0.0128 memory: 1818 2023/02/18 01:38:38 - mmengine - INFO - Epoch(val) [25][180/194] eta: 0:00:01 time: 0.0887 data_time: 0.0201 memory: 1818 2023/02/18 01:38:39 - mmengine - INFO - Epoch(val) [25][194/194] acc/top1: 0.4663 acc/top5: 0.7560 acc/mean1: 0.3995 2023/02/18 01:38:45 - mmengine - INFO - Epoch(train) [26][ 20/1320] lr: 2.0000e-03 eta: 2:21:24 time: 0.3001 data_time: 0.0438 memory: 13708 grad_norm: 4.2714 loss: 1.8092 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8092 2023/02/18 01:38:51 - mmengine - INFO - Epoch(train) [26][ 40/1320] lr: 2.0000e-03 eta: 2:21:18 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.0801 loss: 1.7258 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.7258 2023/02/18 01:38:56 - mmengine - INFO - Epoch(train) [26][ 60/1320] lr: 2.0000e-03 eta: 2:21:13 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 3.9674 loss: 1.6792 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.6792 2023/02/18 01:39:01 - mmengine - INFO - Epoch(train) [26][ 80/1320] lr: 2.0000e-03 eta: 2:21:08 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 3.9428 loss: 1.7496 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7496 2023/02/18 01:39:06 - mmengine - INFO - Epoch(train) [26][ 100/1320] lr: 2.0000e-03 eta: 2:21:03 time: 0.2563 data_time: 0.0118 memory: 13708 grad_norm: 3.9682 loss: 1.6040 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.6040 2023/02/18 01:39:11 - mmengine - INFO - Epoch(train) [26][ 120/1320] lr: 2.0000e-03 eta: 2:20:58 time: 0.2546 data_time: 0.0104 memory: 13708 grad_norm: 3.9813 loss: 1.7135 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.7135 2023/02/18 01:39:16 - mmengine - INFO - Epoch(train) [26][ 140/1320] lr: 2.0000e-03 eta: 2:20:53 time: 0.2553 data_time: 0.0111 memory: 13708 grad_norm: 3.9872 loss: 1.6392 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.6392 2023/02/18 01:39:21 - mmengine - INFO - Epoch(train) [26][ 160/1320] lr: 2.0000e-03 eta: 2:20:47 time: 0.2548 data_time: 0.0108 memory: 13708 grad_norm: 4.0248 loss: 1.4800 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.4800 2023/02/18 01:39:26 - mmengine - INFO - Epoch(train) [26][ 180/1320] lr: 2.0000e-03 eta: 2:20:42 time: 0.2549 data_time: 0.0102 memory: 13708 grad_norm: 4.0482 loss: 1.8090 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.8090 2023/02/18 01:39:31 - mmengine - INFO - Epoch(train) [26][ 200/1320] lr: 2.0000e-03 eta: 2:20:37 time: 0.2555 data_time: 0.0110 memory: 13708 grad_norm: 3.9357 loss: 1.6405 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.6405 2023/02/18 01:39:37 - mmengine - INFO - Epoch(train) [26][ 220/1320] lr: 2.0000e-03 eta: 2:20:32 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 4.0407 loss: 1.5297 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 1.5297 2023/02/18 01:39:42 - mmengine - INFO - Epoch(train) [26][ 240/1320] lr: 2.0000e-03 eta: 2:20:27 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.0180 loss: 1.5769 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.5769 2023/02/18 01:39:47 - mmengine - INFO - Epoch(train) [26][ 260/1320] lr: 2.0000e-03 eta: 2:20:21 time: 0.2565 data_time: 0.0119 memory: 13708 grad_norm: 4.0986 loss: 1.4114 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.4114 2023/02/18 01:39:52 - mmengine - INFO - Epoch(train) [26][ 280/1320] lr: 2.0000e-03 eta: 2:20:16 time: 0.2551 data_time: 0.0102 memory: 13708 grad_norm: 4.1137 loss: 1.3240 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.3240 2023/02/18 01:39:57 - mmengine - INFO - Epoch(train) [26][ 300/1320] lr: 2.0000e-03 eta: 2:20:11 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 4.1264 loss: 1.4473 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4473 2023/02/18 01:40:02 - mmengine - INFO - Epoch(train) [26][ 320/1320] lr: 2.0000e-03 eta: 2:20:06 time: 0.2568 data_time: 0.0123 memory: 13708 grad_norm: 4.0370 loss: 1.5443 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.5443 2023/02/18 01:40:07 - mmengine - INFO - Epoch(train) [26][ 340/1320] lr: 2.0000e-03 eta: 2:20:01 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 4.1249 loss: 1.7798 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.7798 2023/02/18 01:40:12 - mmengine - INFO - Epoch(train) [26][ 360/1320] lr: 2.0000e-03 eta: 2:19:56 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.1804 loss: 1.5956 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.5956 2023/02/18 01:40:18 - mmengine - INFO - Epoch(train) [26][ 380/1320] lr: 2.0000e-03 eta: 2:19:50 time: 0.2555 data_time: 0.0110 memory: 13708 grad_norm: 4.1749 loss: 1.5895 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.5895 2023/02/18 01:40:23 - mmengine - INFO - Epoch(train) [26][ 400/1320] lr: 2.0000e-03 eta: 2:19:45 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.1118 loss: 1.5054 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.5054 2023/02/18 01:40:28 - mmengine - INFO - Epoch(train) [26][ 420/1320] lr: 2.0000e-03 eta: 2:19:40 time: 0.2547 data_time: 0.0106 memory: 13708 grad_norm: 4.0959 loss: 1.4608 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.4608 2023/02/18 01:40:33 - mmengine - INFO - Epoch(train) [26][ 440/1320] lr: 2.0000e-03 eta: 2:19:35 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 4.1646 loss: 1.6206 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.6206 2023/02/18 01:40:38 - mmengine - INFO - Epoch(train) [26][ 460/1320] lr: 2.0000e-03 eta: 2:19:30 time: 0.2559 data_time: 0.0112 memory: 13708 grad_norm: 4.1439 loss: 1.4619 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4619 2023/02/18 01:40:43 - mmengine - INFO - Epoch(train) [26][ 480/1320] lr: 2.0000e-03 eta: 2:19:25 time: 0.2551 data_time: 0.0109 memory: 13708 grad_norm: 4.1691 loss: 1.4491 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.4491 2023/02/18 01:40:48 - mmengine - INFO - Epoch(train) [26][ 500/1320] lr: 2.0000e-03 eta: 2:19:19 time: 0.2553 data_time: 0.0111 memory: 13708 grad_norm: 4.1243 loss: 1.5159 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.5159 2023/02/18 01:40:53 - mmengine - INFO - Epoch(train) [26][ 520/1320] lr: 2.0000e-03 eta: 2:19:14 time: 0.2569 data_time: 0.0118 memory: 13708 grad_norm: 4.2175 loss: 1.4268 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.4268 2023/02/18 01:40:58 - mmengine - INFO - Epoch(train) [26][ 540/1320] lr: 2.0000e-03 eta: 2:19:09 time: 0.2567 data_time: 0.0121 memory: 13708 grad_norm: 4.2585 loss: 1.5260 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.5260 2023/02/18 01:41:04 - mmengine - INFO - Epoch(train) [26][ 560/1320] lr: 2.0000e-03 eta: 2:19:04 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.1554 loss: 1.3937 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.3937 2023/02/18 01:41:09 - mmengine - INFO - Epoch(train) [26][ 580/1320] lr: 2.0000e-03 eta: 2:18:59 time: 0.2570 data_time: 0.0126 memory: 13708 grad_norm: 4.1533 loss: 1.5094 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.5094 2023/02/18 01:41:14 - mmengine - INFO - Epoch(train) [26][ 600/1320] lr: 2.0000e-03 eta: 2:18:54 time: 0.2549 data_time: 0.0104 memory: 13708 grad_norm: 4.1784 loss: 1.4074 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.4074 2023/02/18 01:41:19 - mmengine - INFO - Epoch(train) [26][ 620/1320] lr: 2.0000e-03 eta: 2:18:48 time: 0.2621 data_time: 0.0172 memory: 13708 grad_norm: 4.1589 loss: 1.2732 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2732 2023/02/18 01:41:24 - mmengine - INFO - Epoch(train) [26][ 640/1320] lr: 2.0000e-03 eta: 2:18:43 time: 0.2550 data_time: 0.0108 memory: 13708 grad_norm: 4.1940 loss: 1.4525 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.4525 2023/02/18 01:41:29 - mmengine - INFO - Epoch(train) [26][ 660/1320] lr: 2.0000e-03 eta: 2:18:38 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.1381 loss: 1.4074 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.4074 2023/02/18 01:41:34 - mmengine - INFO - Epoch(train) [26][ 680/1320] lr: 2.0000e-03 eta: 2:18:33 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 4.1544 loss: 1.4411 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4411 2023/02/18 01:41:39 - mmengine - INFO - Epoch(train) [26][ 700/1320] lr: 2.0000e-03 eta: 2:18:28 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 4.2819 loss: 1.4402 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.4402 2023/02/18 01:41:45 - mmengine - INFO - Epoch(train) [26][ 720/1320] lr: 2.0000e-03 eta: 2:18:23 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 4.2708 loss: 1.5079 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.5079 2023/02/18 01:41:50 - mmengine - INFO - Epoch(train) [26][ 740/1320] lr: 2.0000e-03 eta: 2:18:17 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.2525 loss: 1.3495 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3495 2023/02/18 01:41:55 - mmengine - INFO - Epoch(train) [26][ 760/1320] lr: 2.0000e-03 eta: 2:18:12 time: 0.2557 data_time: 0.0104 memory: 13708 grad_norm: 4.2687 loss: 1.4012 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.4012 2023/02/18 01:42:00 - mmengine - INFO - Epoch(train) [26][ 780/1320] lr: 2.0000e-03 eta: 2:18:07 time: 0.2552 data_time: 0.0111 memory: 13708 grad_norm: 4.2158 loss: 1.5527 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.5527 2023/02/18 01:42:05 - mmengine - INFO - Epoch(train) [26][ 800/1320] lr: 2.0000e-03 eta: 2:18:02 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 4.4281 loss: 1.7884 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.7884 2023/02/18 01:42:10 - mmengine - INFO - Epoch(train) [26][ 820/1320] lr: 2.0000e-03 eta: 2:17:57 time: 0.2563 data_time: 0.0113 memory: 13708 grad_norm: 4.2746 loss: 1.5154 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.5154 2023/02/18 01:42:15 - mmengine - INFO - Epoch(train) [26][ 840/1320] lr: 2.0000e-03 eta: 2:17:52 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 4.3323 loss: 1.5848 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.5848 2023/02/18 01:42:20 - mmengine - INFO - Epoch(train) [26][ 860/1320] lr: 2.0000e-03 eta: 2:17:46 time: 0.2566 data_time: 0.0121 memory: 13708 grad_norm: 4.1351 loss: 1.4237 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.4237 2023/02/18 01:42:26 - mmengine - INFO - Epoch(train) [26][ 880/1320] lr: 2.0000e-03 eta: 2:17:41 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 4.2860 loss: 1.2203 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.2203 2023/02/18 01:42:31 - mmengine - INFO - Epoch(train) [26][ 900/1320] lr: 2.0000e-03 eta: 2:17:36 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.2086 loss: 1.3611 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.3611 2023/02/18 01:42:36 - mmengine - INFO - Epoch(train) [26][ 920/1320] lr: 2.0000e-03 eta: 2:17:31 time: 0.2554 data_time: 0.0103 memory: 13708 grad_norm: 4.3319 loss: 1.6223 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.6223 2023/02/18 01:42:41 - mmengine - INFO - Epoch(train) [26][ 940/1320] lr: 2.0000e-03 eta: 2:17:26 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 4.1449 loss: 1.2213 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2213 2023/02/18 01:42:46 - mmengine - INFO - Epoch(train) [26][ 960/1320] lr: 2.0000e-03 eta: 2:17:20 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.2362 loss: 1.3622 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3622 2023/02/18 01:42:51 - mmengine - INFO - Epoch(train) [26][ 980/1320] lr: 2.0000e-03 eta: 2:17:15 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.2574 loss: 1.2304 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.2304 2023/02/18 01:42:56 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:42:56 - mmengine - INFO - Epoch(train) [26][1000/1320] lr: 2.0000e-03 eta: 2:17:10 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 4.3767 loss: 1.5690 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.5690 2023/02/18 01:43:01 - mmengine - INFO - Epoch(train) [26][1020/1320] lr: 2.0000e-03 eta: 2:17:05 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.3465 loss: 1.3258 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3258 2023/02/18 01:43:06 - mmengine - INFO - Epoch(train) [26][1040/1320] lr: 2.0000e-03 eta: 2:17:00 time: 0.2557 data_time: 0.0113 memory: 13708 grad_norm: 4.3298 loss: 1.4786 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4786 2023/02/18 01:43:12 - mmengine - INFO - Epoch(train) [26][1060/1320] lr: 2.0000e-03 eta: 2:16:55 time: 0.2554 data_time: 0.0102 memory: 13708 grad_norm: 4.2774 loss: 1.5566 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.5566 2023/02/18 01:43:17 - mmengine - INFO - Epoch(train) [26][1080/1320] lr: 2.0000e-03 eta: 2:16:49 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 4.3834 loss: 1.5547 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.5547 2023/02/18 01:43:22 - mmengine - INFO - Epoch(train) [26][1100/1320] lr: 2.0000e-03 eta: 2:16:44 time: 0.2585 data_time: 0.0137 memory: 13708 grad_norm: 4.2783 loss: 1.3908 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3908 2023/02/18 01:43:27 - mmengine - INFO - Epoch(train) [26][1120/1320] lr: 2.0000e-03 eta: 2:16:39 time: 0.2553 data_time: 0.0111 memory: 13708 grad_norm: 4.2392 loss: 1.3949 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3949 2023/02/18 01:43:32 - mmengine - INFO - Epoch(train) [26][1140/1320] lr: 2.0000e-03 eta: 2:16:34 time: 0.2559 data_time: 0.0115 memory: 13708 grad_norm: 4.3069 loss: 1.3537 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.3537 2023/02/18 01:43:37 - mmengine - INFO - Epoch(train) [26][1160/1320] lr: 2.0000e-03 eta: 2:16:29 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.3973 loss: 1.6178 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.6178 2023/02/18 01:43:42 - mmengine - INFO - Epoch(train) [26][1180/1320] lr: 2.0000e-03 eta: 2:16:24 time: 0.2546 data_time: 0.0103 memory: 13708 grad_norm: 4.3539 loss: 1.4520 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.4520 2023/02/18 01:43:47 - mmengine - INFO - Epoch(train) [26][1200/1320] lr: 2.0000e-03 eta: 2:16:18 time: 0.2553 data_time: 0.0105 memory: 13708 grad_norm: 4.3361 loss: 1.4782 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.4782 2023/02/18 01:43:53 - mmengine - INFO - Epoch(train) [26][1220/1320] lr: 2.0000e-03 eta: 2:16:13 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 4.3030 loss: 1.5233 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.5233 2023/02/18 01:43:58 - mmengine - INFO - Epoch(train) [26][1240/1320] lr: 2.0000e-03 eta: 2:16:08 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 4.2727 loss: 1.3730 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.3730 2023/02/18 01:44:03 - mmengine - INFO - Epoch(train) [26][1260/1320] lr: 2.0000e-03 eta: 2:16:03 time: 0.2556 data_time: 0.0111 memory: 13708 grad_norm: 4.2225 loss: 1.3242 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.3242 2023/02/18 01:44:08 - mmengine - INFO - Epoch(train) [26][1280/1320] lr: 2.0000e-03 eta: 2:15:58 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.3182 loss: 1.4704 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4704 2023/02/18 01:44:13 - mmengine - INFO - Epoch(train) [26][1300/1320] lr: 2.0000e-03 eta: 2:15:53 time: 0.2562 data_time: 0.0110 memory: 13708 grad_norm: 4.1906 loss: 1.3422 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3422 2023/02/18 01:44:18 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:44:18 - mmengine - INFO - Epoch(train) [26][1320/1320] lr: 2.0000e-03 eta: 2:15:47 time: 0.2517 data_time: 0.0107 memory: 13708 grad_norm: 4.2290 loss: 1.5745 top1_acc: 0.6364 top5_acc: 0.9091 loss_cls: 1.5745 2023/02/18 01:44:21 - mmengine - INFO - Epoch(val) [26][ 20/194] eta: 0:00:21 time: 0.1242 data_time: 0.0555 memory: 1818 2023/02/18 01:44:22 - mmengine - INFO - Epoch(val) [26][ 40/194] eta: 0:00:16 time: 0.0888 data_time: 0.0187 memory: 1818 2023/02/18 01:44:24 - mmengine - INFO - Epoch(val) [26][ 60/194] eta: 0:00:13 time: 0.0865 data_time: 0.0181 memory: 1818 2023/02/18 01:44:26 - mmengine - INFO - Epoch(val) [26][ 80/194] eta: 0:00:10 time: 0.0848 data_time: 0.0166 memory: 1818 2023/02/18 01:44:28 - mmengine - INFO - Epoch(val) [26][100/194] eta: 0:00:08 time: 0.0892 data_time: 0.0204 memory: 1818 2023/02/18 01:44:29 - mmengine - INFO - Epoch(val) [26][120/194] eta: 0:00:06 time: 0.0839 data_time: 0.0150 memory: 1818 2023/02/18 01:44:31 - mmengine - INFO - Epoch(val) [26][140/194] eta: 0:00:04 time: 0.0886 data_time: 0.0203 memory: 1818 2023/02/18 01:44:33 - mmengine - INFO - Epoch(val) [26][160/194] eta: 0:00:03 time: 0.0814 data_time: 0.0127 memory: 1818 2023/02/18 01:44:34 - mmengine - INFO - Epoch(val) [26][180/194] eta: 0:00:01 time: 0.0873 data_time: 0.0189 memory: 1818 2023/02/18 01:44:36 - mmengine - INFO - Epoch(val) [26][194/194] acc/top1: 0.5662 acc/top5: 0.8332 acc/mean1: 0.4954 2023/02/18 01:44:36 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_21.pth is removed 2023/02/18 01:44:37 - mmengine - INFO - The best checkpoint with 0.5662 acc/top1 at 26 epoch is saved to best_acc/top1_epoch_26.pth. 2023/02/18 01:44:43 - mmengine - INFO - Epoch(train) [27][ 20/1320] lr: 2.0000e-03 eta: 2:15:43 time: 0.2957 data_time: 0.0422 memory: 13708 grad_norm: 4.2685 loss: 1.3194 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3194 2023/02/18 01:44:48 - mmengine - INFO - Epoch(train) [27][ 40/1320] lr: 2.0000e-03 eta: 2:15:38 time: 0.2556 data_time: 0.0102 memory: 13708 grad_norm: 4.1931 loss: 1.3707 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3707 2023/02/18 01:44:53 - mmengine - INFO - Epoch(train) [27][ 60/1320] lr: 2.0000e-03 eta: 2:15:33 time: 0.2566 data_time: 0.0120 memory: 13708 grad_norm: 4.1946 loss: 1.3984 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3984 2023/02/18 01:44:59 - mmengine - INFO - Epoch(train) [27][ 80/1320] lr: 2.0000e-03 eta: 2:15:27 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 4.3152 loss: 1.3202 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3202 2023/02/18 01:45:04 - mmengine - INFO - Epoch(train) [27][ 100/1320] lr: 2.0000e-03 eta: 2:15:22 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 4.3576 loss: 1.4940 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 1.4940 2023/02/18 01:45:09 - mmengine - INFO - Epoch(train) [27][ 120/1320] lr: 2.0000e-03 eta: 2:15:17 time: 0.2556 data_time: 0.0111 memory: 13708 grad_norm: 4.3237 loss: 1.5698 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.5698 2023/02/18 01:45:14 - mmengine - INFO - Epoch(train) [27][ 140/1320] lr: 2.0000e-03 eta: 2:15:12 time: 0.2550 data_time: 0.0100 memory: 13708 grad_norm: 4.1506 loss: 1.4520 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.4520 2023/02/18 01:45:19 - mmengine - INFO - Epoch(train) [27][ 160/1320] lr: 2.0000e-03 eta: 2:15:07 time: 0.2566 data_time: 0.0120 memory: 13708 grad_norm: 4.3763 loss: 1.5367 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.5367 2023/02/18 01:45:24 - mmengine - INFO - Epoch(train) [27][ 180/1320] lr: 2.0000e-03 eta: 2:15:02 time: 0.2560 data_time: 0.0107 memory: 13708 grad_norm: 4.3279 loss: 1.4076 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4076 2023/02/18 01:45:29 - mmengine - INFO - Epoch(train) [27][ 200/1320] lr: 2.0000e-03 eta: 2:14:56 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.2218 loss: 1.2775 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2775 2023/02/18 01:45:34 - mmengine - INFO - Epoch(train) [27][ 220/1320] lr: 2.0000e-03 eta: 2:14:51 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 4.2828 loss: 1.3153 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.3153 2023/02/18 01:45:39 - mmengine - INFO - Epoch(train) [27][ 240/1320] lr: 2.0000e-03 eta: 2:14:46 time: 0.2564 data_time: 0.0105 memory: 13708 grad_norm: 4.3013 loss: 1.4978 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4978 2023/02/18 01:45:45 - mmengine - INFO - Epoch(train) [27][ 260/1320] lr: 2.0000e-03 eta: 2:14:41 time: 0.2565 data_time: 0.0107 memory: 13708 grad_norm: 4.4993 loss: 1.4201 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.4201 2023/02/18 01:45:50 - mmengine - INFO - Epoch(train) [27][ 280/1320] lr: 2.0000e-03 eta: 2:14:36 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.3410 loss: 1.4674 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4674 2023/02/18 01:45:55 - mmengine - INFO - Epoch(train) [27][ 300/1320] lr: 2.0000e-03 eta: 2:14:31 time: 0.2565 data_time: 0.0113 memory: 13708 grad_norm: 4.3625 loss: 1.4373 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4373 2023/02/18 01:46:00 - mmengine - INFO - Epoch(train) [27][ 320/1320] lr: 2.0000e-03 eta: 2:14:25 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.3121 loss: 1.3563 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3563 2023/02/18 01:46:05 - mmengine - INFO - Epoch(train) [27][ 340/1320] lr: 2.0000e-03 eta: 2:14:20 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 4.3616 loss: 1.4606 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.4606 2023/02/18 01:46:10 - mmengine - INFO - Epoch(train) [27][ 360/1320] lr: 2.0000e-03 eta: 2:14:15 time: 0.2553 data_time: 0.0111 memory: 13708 grad_norm: 4.4411 loss: 1.4056 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4056 2023/02/18 01:46:15 - mmengine - INFO - Epoch(train) [27][ 380/1320] lr: 2.0000e-03 eta: 2:14:10 time: 0.2559 data_time: 0.0113 memory: 13708 grad_norm: 4.3447 loss: 1.3244 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3244 2023/02/18 01:46:20 - mmengine - INFO - Epoch(train) [27][ 400/1320] lr: 2.0000e-03 eta: 2:14:05 time: 0.2577 data_time: 0.0127 memory: 13708 grad_norm: 4.2544 loss: 1.2030 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2030 2023/02/18 01:46:26 - mmengine - INFO - Epoch(train) [27][ 420/1320] lr: 2.0000e-03 eta: 2:14:00 time: 0.2553 data_time: 0.0105 memory: 13708 grad_norm: 4.3080 loss: 1.5702 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.5702 2023/02/18 01:46:31 - mmengine - INFO - Epoch(train) [27][ 440/1320] lr: 2.0000e-03 eta: 2:13:54 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 4.4296 loss: 1.4925 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4925 2023/02/18 01:46:36 - mmengine - INFO - Epoch(train) [27][ 460/1320] lr: 2.0000e-03 eta: 2:13:49 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.4579 loss: 1.3428 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3428 2023/02/18 01:46:41 - mmengine - INFO - Epoch(train) [27][ 480/1320] lr: 2.0000e-03 eta: 2:13:44 time: 0.2552 data_time: 0.0110 memory: 13708 grad_norm: 4.3050 loss: 1.3336 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.3336 2023/02/18 01:46:46 - mmengine - INFO - Epoch(train) [27][ 500/1320] lr: 2.0000e-03 eta: 2:13:39 time: 0.2576 data_time: 0.0128 memory: 13708 grad_norm: 4.3553 loss: 1.5053 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.5053 2023/02/18 01:46:51 - mmengine - INFO - Epoch(train) [27][ 520/1320] lr: 2.0000e-03 eta: 2:13:34 time: 0.2554 data_time: 0.0110 memory: 13708 grad_norm: 4.3346 loss: 1.4757 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.4757 2023/02/18 01:46:56 - mmengine - INFO - Epoch(train) [27][ 540/1320] lr: 2.0000e-03 eta: 2:13:28 time: 0.2554 data_time: 0.0103 memory: 13708 grad_norm: 4.4059 loss: 1.5049 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.5049 2023/02/18 01:47:01 - mmengine - INFO - Epoch(train) [27][ 560/1320] lr: 2.0000e-03 eta: 2:13:23 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 4.3057 loss: 1.4179 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 1.4179 2023/02/18 01:47:07 - mmengine - INFO - Epoch(train) [27][ 580/1320] lr: 2.0000e-03 eta: 2:13:18 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 4.3816 loss: 1.4761 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.4761 2023/02/18 01:47:12 - mmengine - INFO - Epoch(train) [27][ 600/1320] lr: 2.0000e-03 eta: 2:13:13 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 4.3614 loss: 1.3916 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.3916 2023/02/18 01:47:17 - mmengine - INFO - Epoch(train) [27][ 620/1320] lr: 2.0000e-03 eta: 2:13:08 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.4201 loss: 1.3947 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.3947 2023/02/18 01:47:22 - mmengine - INFO - Epoch(train) [27][ 640/1320] lr: 2.0000e-03 eta: 2:13:03 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 4.5257 loss: 1.5000 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.5000 2023/02/18 01:47:27 - mmengine - INFO - Epoch(train) [27][ 660/1320] lr: 2.0000e-03 eta: 2:12:57 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 4.2102 loss: 1.2151 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2151 2023/02/18 01:47:32 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:47:32 - mmengine - INFO - Epoch(train) [27][ 680/1320] lr: 2.0000e-03 eta: 2:12:52 time: 0.2552 data_time: 0.0103 memory: 13708 grad_norm: 4.5084 loss: 1.4523 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.4523 2023/02/18 01:47:37 - mmengine - INFO - Epoch(train) [27][ 700/1320] lr: 2.0000e-03 eta: 2:12:47 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.3342 loss: 1.2933 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2933 2023/02/18 01:47:42 - mmengine - INFO - Epoch(train) [27][ 720/1320] lr: 2.0000e-03 eta: 2:12:42 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.3486 loss: 1.4748 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.4748 2023/02/18 01:47:47 - mmengine - INFO - Epoch(train) [27][ 740/1320] lr: 2.0000e-03 eta: 2:12:37 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.3867 loss: 1.2367 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2367 2023/02/18 01:47:53 - mmengine - INFO - Epoch(train) [27][ 760/1320] lr: 2.0000e-03 eta: 2:12:32 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 4.3279 loss: 1.3635 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3635 2023/02/18 01:47:58 - mmengine - INFO - Epoch(train) [27][ 780/1320] lr: 2.0000e-03 eta: 2:12:26 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.4241 loss: 1.5678 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.5678 2023/02/18 01:48:03 - mmengine - INFO - Epoch(train) [27][ 800/1320] lr: 2.0000e-03 eta: 2:12:21 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 4.4536 loss: 1.3551 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3551 2023/02/18 01:48:08 - mmengine - INFO - Epoch(train) [27][ 820/1320] lr: 2.0000e-03 eta: 2:12:16 time: 0.2558 data_time: 0.0106 memory: 13708 grad_norm: 4.3341 loss: 1.2956 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.2956 2023/02/18 01:48:13 - mmengine - INFO - Epoch(train) [27][ 840/1320] lr: 2.0000e-03 eta: 2:12:11 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 4.5750 loss: 1.5230 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.5230 2023/02/18 01:48:18 - mmengine - INFO - Epoch(train) [27][ 860/1320] lr: 2.0000e-03 eta: 2:12:06 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 4.4220 loss: 1.3014 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.3014 2023/02/18 01:48:23 - mmengine - INFO - Epoch(train) [27][ 880/1320] lr: 2.0000e-03 eta: 2:12:01 time: 0.2560 data_time: 0.0105 memory: 13708 grad_norm: 4.3705 loss: 1.3768 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3768 2023/02/18 01:48:28 - mmengine - INFO - Epoch(train) [27][ 900/1320] lr: 2.0000e-03 eta: 2:11:55 time: 0.2557 data_time: 0.0114 memory: 13708 grad_norm: 4.3128 loss: 1.2830 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2830 2023/02/18 01:48:33 - mmengine - INFO - Epoch(train) [27][ 920/1320] lr: 2.0000e-03 eta: 2:11:50 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 4.3996 loss: 1.4110 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.4110 2023/02/18 01:48:39 - mmengine - INFO - Epoch(train) [27][ 940/1320] lr: 2.0000e-03 eta: 2:11:45 time: 0.2553 data_time: 0.0105 memory: 13708 grad_norm: 4.3588 loss: 1.3676 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.3676 2023/02/18 01:48:44 - mmengine - INFO - Epoch(train) [27][ 960/1320] lr: 2.0000e-03 eta: 2:11:40 time: 0.2557 data_time: 0.0103 memory: 13708 grad_norm: 4.3527 loss: 1.3061 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.3061 2023/02/18 01:48:49 - mmengine - INFO - Epoch(train) [27][ 980/1320] lr: 2.0000e-03 eta: 2:11:35 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.5285 loss: 1.4441 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.4441 2023/02/18 01:48:54 - mmengine - INFO - Epoch(train) [27][1000/1320] lr: 2.0000e-03 eta: 2:11:30 time: 0.2606 data_time: 0.0154 memory: 13708 grad_norm: 4.3744 loss: 1.4824 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.4824 2023/02/18 01:48:59 - mmengine - INFO - Epoch(train) [27][1020/1320] lr: 2.0000e-03 eta: 2:11:24 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 4.3798 loss: 1.3272 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3272 2023/02/18 01:49:04 - mmengine - INFO - Epoch(train) [27][1040/1320] lr: 2.0000e-03 eta: 2:11:19 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.4515 loss: 1.4985 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.4985 2023/02/18 01:49:09 - mmengine - INFO - Epoch(train) [27][1060/1320] lr: 2.0000e-03 eta: 2:11:14 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 4.3995 loss: 1.4225 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.4225 2023/02/18 01:49:14 - mmengine - INFO - Epoch(train) [27][1080/1320] lr: 2.0000e-03 eta: 2:11:09 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.3839 loss: 1.3997 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3997 2023/02/18 01:49:20 - mmengine - INFO - Epoch(train) [27][1100/1320] lr: 2.0000e-03 eta: 2:11:04 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 4.5076 loss: 1.2195 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2195 2023/02/18 01:49:25 - mmengine - INFO - Epoch(train) [27][1120/1320] lr: 2.0000e-03 eta: 2:10:59 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 4.5542 loss: 1.2536 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2536 2023/02/18 01:49:30 - mmengine - INFO - Epoch(train) [27][1140/1320] lr: 2.0000e-03 eta: 2:10:53 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.5085 loss: 1.4353 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.4353 2023/02/18 01:49:35 - mmengine - INFO - Epoch(train) [27][1160/1320] lr: 2.0000e-03 eta: 2:10:48 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 4.5088 loss: 1.3653 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3653 2023/02/18 01:49:40 - mmengine - INFO - Epoch(train) [27][1180/1320] lr: 2.0000e-03 eta: 2:10:43 time: 0.2569 data_time: 0.0117 memory: 13708 grad_norm: 4.3784 loss: 1.4116 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.4116 2023/02/18 01:49:45 - mmengine - INFO - Epoch(train) [27][1200/1320] lr: 2.0000e-03 eta: 2:10:38 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.3470 loss: 1.3084 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3084 2023/02/18 01:49:50 - mmengine - INFO - Epoch(train) [27][1220/1320] lr: 2.0000e-03 eta: 2:10:33 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.3820 loss: 1.2546 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2546 2023/02/18 01:49:55 - mmengine - INFO - Epoch(train) [27][1240/1320] lr: 2.0000e-03 eta: 2:10:28 time: 0.2567 data_time: 0.0114 memory: 13708 grad_norm: 4.5264 loss: 1.5805 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.5805 2023/02/18 01:50:01 - mmengine - INFO - Epoch(train) [27][1260/1320] lr: 2.0000e-03 eta: 2:10:22 time: 0.2553 data_time: 0.0104 memory: 13708 grad_norm: 4.3883 loss: 1.3883 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.3883 2023/02/18 01:50:06 - mmengine - INFO - Epoch(train) [27][1280/1320] lr: 2.0000e-03 eta: 2:10:17 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 4.4951 loss: 1.3621 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.3621 2023/02/18 01:50:11 - mmengine - INFO - Epoch(train) [27][1300/1320] lr: 2.0000e-03 eta: 2:10:12 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 4.4718 loss: 1.3806 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.3806 2023/02/18 01:50:16 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:50:16 - mmengine - INFO - Epoch(train) [27][1320/1320] lr: 2.0000e-03 eta: 2:10:07 time: 0.2522 data_time: 0.0112 memory: 13708 grad_norm: 4.6205 loss: 1.2268 top1_acc: 0.6364 top5_acc: 0.9091 loss_cls: 1.2268 2023/02/18 01:50:16 - mmengine - INFO - Saving checkpoint at 27 epochs 2023/02/18 01:50:20 - mmengine - INFO - Epoch(val) [27][ 20/194] eta: 0:00:22 time: 0.1296 data_time: 0.0612 memory: 1818 2023/02/18 01:50:21 - mmengine - INFO - Epoch(val) [27][ 40/194] eta: 0:00:16 time: 0.0880 data_time: 0.0197 memory: 1818 2023/02/18 01:50:23 - mmengine - INFO - Epoch(val) [27][ 60/194] eta: 0:00:13 time: 0.0918 data_time: 0.0226 memory: 1818 2023/02/18 01:50:25 - mmengine - INFO - Epoch(val) [27][ 80/194] eta: 0:00:11 time: 0.0840 data_time: 0.0148 memory: 1818 2023/02/18 01:50:27 - mmengine - INFO - Epoch(val) [27][100/194] eta: 0:00:09 time: 0.0946 data_time: 0.0259 memory: 1818 2023/02/18 01:50:28 - mmengine - INFO - Epoch(val) [27][120/194] eta: 0:00:07 time: 0.0827 data_time: 0.0151 memory: 1818 2023/02/18 01:50:30 - mmengine - INFO - Epoch(val) [27][140/194] eta: 0:00:05 time: 0.0907 data_time: 0.0217 memory: 1818 2023/02/18 01:50:32 - mmengine - INFO - Epoch(val) [27][160/194] eta: 0:00:03 time: 0.0809 data_time: 0.0125 memory: 1818 2023/02/18 01:50:33 - mmengine - INFO - Epoch(val) [27][180/194] eta: 0:00:01 time: 0.0826 data_time: 0.0158 memory: 1818 2023/02/18 01:50:35 - mmengine - INFO - Epoch(val) [27][194/194] acc/top1: 0.5746 acc/top5: 0.8409 acc/mean1: 0.5060 2023/02/18 01:50:35 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_26.pth is removed 2023/02/18 01:50:36 - mmengine - INFO - The best checkpoint with 0.5746 acc/top1 at 27 epoch is saved to best_acc/top1_epoch_27.pth. 2023/02/18 01:50:42 - mmengine - INFO - Epoch(train) [28][ 20/1320] lr: 2.0000e-03 eta: 2:10:02 time: 0.2934 data_time: 0.0410 memory: 13708 grad_norm: 4.4610 loss: 1.2983 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2983 2023/02/18 01:50:47 - mmengine - INFO - Epoch(train) [28][ 40/1320] lr: 2.0000e-03 eta: 2:09:57 time: 0.2551 data_time: 0.0103 memory: 13708 grad_norm: 4.4404 loss: 1.3924 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.3924 2023/02/18 01:50:52 - mmengine - INFO - Epoch(train) [28][ 60/1320] lr: 2.0000e-03 eta: 2:09:52 time: 0.2564 data_time: 0.0112 memory: 13708 grad_norm: 4.4261 loss: 1.3452 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3452 2023/02/18 01:50:57 - mmengine - INFO - Epoch(train) [28][ 80/1320] lr: 2.0000e-03 eta: 2:09:47 time: 0.2549 data_time: 0.0099 memory: 13708 grad_norm: 4.3751 loss: 1.1561 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1561 2023/02/18 01:51:02 - mmengine - INFO - Epoch(train) [28][ 100/1320] lr: 2.0000e-03 eta: 2:09:42 time: 0.2551 data_time: 0.0101 memory: 13708 grad_norm: 4.4129 loss: 1.3267 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3267 2023/02/18 01:51:07 - mmengine - INFO - Epoch(train) [28][ 120/1320] lr: 2.0000e-03 eta: 2:09:37 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 4.4490 loss: 1.3666 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.3666 2023/02/18 01:51:13 - mmengine - INFO - Epoch(train) [28][ 140/1320] lr: 2.0000e-03 eta: 2:09:31 time: 0.2549 data_time: 0.0104 memory: 13708 grad_norm: 4.5280 loss: 1.2969 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2969 2023/02/18 01:51:18 - mmengine - INFO - Epoch(train) [28][ 160/1320] lr: 2.0000e-03 eta: 2:09:26 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.4165 loss: 1.2623 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2623 2023/02/18 01:51:23 - mmengine - INFO - Epoch(train) [28][ 180/1320] lr: 2.0000e-03 eta: 2:09:21 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.5275 loss: 1.2219 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2219 2023/02/18 01:51:28 - mmengine - INFO - Epoch(train) [28][ 200/1320] lr: 2.0000e-03 eta: 2:09:16 time: 0.2552 data_time: 0.0104 memory: 13708 grad_norm: 4.4508 loss: 1.2678 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2678 2023/02/18 01:51:33 - mmengine - INFO - Epoch(train) [28][ 220/1320] lr: 2.0000e-03 eta: 2:09:11 time: 0.2586 data_time: 0.0132 memory: 13708 grad_norm: 4.5137 loss: 1.3521 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3521 2023/02/18 01:51:38 - mmengine - INFO - Epoch(train) [28][ 240/1320] lr: 2.0000e-03 eta: 2:09:06 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.3944 loss: 1.1169 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1169 2023/02/18 01:51:43 - mmengine - INFO - Epoch(train) [28][ 260/1320] lr: 2.0000e-03 eta: 2:09:00 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 4.5055 loss: 1.2916 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2916 2023/02/18 01:51:48 - mmengine - INFO - Epoch(train) [28][ 280/1320] lr: 2.0000e-03 eta: 2:08:55 time: 0.2567 data_time: 0.0124 memory: 13708 grad_norm: 4.5259 loss: 1.4958 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4958 2023/02/18 01:51:54 - mmengine - INFO - Epoch(train) [28][ 300/1320] lr: 2.0000e-03 eta: 2:08:50 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.5427 loss: 1.3622 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3622 2023/02/18 01:51:59 - mmengine - INFO - Epoch(train) [28][ 320/1320] lr: 2.0000e-03 eta: 2:08:45 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 4.6514 loss: 1.3987 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.3987 2023/02/18 01:52:04 - mmengine - INFO - Epoch(train) [28][ 340/1320] lr: 2.0000e-03 eta: 2:08:40 time: 0.2560 data_time: 0.0113 memory: 13708 grad_norm: 4.6182 loss: 1.3428 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.3428 2023/02/18 01:52:09 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:52:09 - mmengine - INFO - Epoch(train) [28][ 360/1320] lr: 2.0000e-03 eta: 2:08:35 time: 0.2558 data_time: 0.0106 memory: 13708 grad_norm: 4.4717 loss: 1.2894 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2894 2023/02/18 01:52:14 - mmengine - INFO - Epoch(train) [28][ 380/1320] lr: 2.0000e-03 eta: 2:08:29 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 4.5194 loss: 1.4730 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.4730 2023/02/18 01:52:19 - mmengine - INFO - Epoch(train) [28][ 400/1320] lr: 2.0000e-03 eta: 2:08:24 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 4.5404 loss: 1.2086 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.2086 2023/02/18 01:52:24 - mmengine - INFO - Epoch(train) [28][ 420/1320] lr: 2.0000e-03 eta: 2:08:19 time: 0.2556 data_time: 0.0111 memory: 13708 grad_norm: 4.4944 loss: 1.2690 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2690 2023/02/18 01:52:29 - mmengine - INFO - Epoch(train) [28][ 440/1320] lr: 2.0000e-03 eta: 2:08:14 time: 0.2556 data_time: 0.0112 memory: 13708 grad_norm: 4.5207 loss: 1.3717 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3717 2023/02/18 01:52:34 - mmengine - INFO - Epoch(train) [28][ 460/1320] lr: 2.0000e-03 eta: 2:08:09 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.6937 loss: 1.2703 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2703 2023/02/18 01:52:40 - mmengine - INFO - Epoch(train) [28][ 480/1320] lr: 2.0000e-03 eta: 2:08:04 time: 0.2573 data_time: 0.0128 memory: 13708 grad_norm: 4.5316 loss: 1.1379 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1379 2023/02/18 01:52:45 - mmengine - INFO - Epoch(train) [28][ 500/1320] lr: 2.0000e-03 eta: 2:07:58 time: 0.2558 data_time: 0.0113 memory: 13708 grad_norm: 4.4769 loss: 1.3264 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.3264 2023/02/18 01:52:50 - mmengine - INFO - Epoch(train) [28][ 520/1320] lr: 2.0000e-03 eta: 2:07:53 time: 0.2552 data_time: 0.0110 memory: 13708 grad_norm: 4.6302 loss: 1.2129 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2129 2023/02/18 01:52:55 - mmengine - INFO - Epoch(train) [28][ 540/1320] lr: 2.0000e-03 eta: 2:07:48 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.4445 loss: 1.3194 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3194 2023/02/18 01:53:00 - mmengine - INFO - Epoch(train) [28][ 560/1320] lr: 2.0000e-03 eta: 2:07:43 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.5527 loss: 1.3492 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3492 2023/02/18 01:53:05 - mmengine - INFO - Epoch(train) [28][ 580/1320] lr: 2.0000e-03 eta: 2:07:38 time: 0.2556 data_time: 0.0102 memory: 13708 grad_norm: 4.3429 loss: 1.3086 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3086 2023/02/18 01:53:10 - mmengine - INFO - Epoch(train) [28][ 600/1320] lr: 2.0000e-03 eta: 2:07:32 time: 0.2558 data_time: 0.0112 memory: 13708 grad_norm: 4.5004 loss: 1.3013 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.3013 2023/02/18 01:53:15 - mmengine - INFO - Epoch(train) [28][ 620/1320] lr: 2.0000e-03 eta: 2:07:27 time: 0.2565 data_time: 0.0121 memory: 13708 grad_norm: 4.6031 loss: 1.2281 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2281 2023/02/18 01:53:21 - mmengine - INFO - Epoch(train) [28][ 640/1320] lr: 2.0000e-03 eta: 2:07:22 time: 0.2549 data_time: 0.0105 memory: 13708 grad_norm: 4.5041 loss: 1.3535 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3535 2023/02/18 01:53:26 - mmengine - INFO - Epoch(train) [28][ 660/1320] lr: 2.0000e-03 eta: 2:07:17 time: 0.2557 data_time: 0.0111 memory: 13708 grad_norm: 4.5524 loss: 1.3317 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3317 2023/02/18 01:53:31 - mmengine - INFO - Epoch(train) [28][ 680/1320] lr: 2.0000e-03 eta: 2:07:12 time: 0.2552 data_time: 0.0103 memory: 13708 grad_norm: 4.6482 loss: 1.2811 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2811 2023/02/18 01:53:36 - mmengine - INFO - Epoch(train) [28][ 700/1320] lr: 2.0000e-03 eta: 2:07:07 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 4.6216 loss: 1.3121 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.3121 2023/02/18 01:53:41 - mmengine - INFO - Epoch(train) [28][ 720/1320] lr: 2.0000e-03 eta: 2:07:01 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.4551 loss: 1.2352 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2352 2023/02/18 01:53:46 - mmengine - INFO - Epoch(train) [28][ 740/1320] lr: 2.0000e-03 eta: 2:06:56 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 4.7099 loss: 1.4314 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.4314 2023/02/18 01:53:51 - mmengine - INFO - Epoch(train) [28][ 760/1320] lr: 2.0000e-03 eta: 2:06:51 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 4.5773 loss: 1.2677 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 1.2677 2023/02/18 01:53:56 - mmengine - INFO - Epoch(train) [28][ 780/1320] lr: 2.0000e-03 eta: 2:06:46 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.6654 loss: 1.3512 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3512 2023/02/18 01:54:01 - mmengine - INFO - Epoch(train) [28][ 800/1320] lr: 2.0000e-03 eta: 2:06:41 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 4.5888 loss: 1.2787 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2787 2023/02/18 01:54:07 - mmengine - INFO - Epoch(train) [28][ 820/1320] lr: 2.0000e-03 eta: 2:06:36 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.5779 loss: 1.2814 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.2814 2023/02/18 01:54:12 - mmengine - INFO - Epoch(train) [28][ 840/1320] lr: 2.0000e-03 eta: 2:06:30 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 4.7173 loss: 1.3186 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.3186 2023/02/18 01:54:17 - mmengine - INFO - Epoch(train) [28][ 860/1320] lr: 2.0000e-03 eta: 2:06:25 time: 0.2568 data_time: 0.0111 memory: 13708 grad_norm: 4.6883 loss: 1.3116 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3116 2023/02/18 01:54:22 - mmengine - INFO - Epoch(train) [28][ 880/1320] lr: 2.0000e-03 eta: 2:06:20 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 4.3553 loss: 1.2125 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2125 2023/02/18 01:54:27 - mmengine - INFO - Epoch(train) [28][ 900/1320] lr: 2.0000e-03 eta: 2:06:15 time: 0.2548 data_time: 0.0106 memory: 13708 grad_norm: 4.6264 loss: 1.2288 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2288 2023/02/18 01:54:32 - mmengine - INFO - Epoch(train) [28][ 920/1320] lr: 2.0000e-03 eta: 2:06:10 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 4.4638 loss: 1.1816 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1816 2023/02/18 01:54:37 - mmengine - INFO - Epoch(train) [28][ 940/1320] lr: 2.0000e-03 eta: 2:06:05 time: 0.2563 data_time: 0.0116 memory: 13708 grad_norm: 4.4456 loss: 1.2655 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2655 2023/02/18 01:54:42 - mmengine - INFO - Epoch(train) [28][ 960/1320] lr: 2.0000e-03 eta: 2:06:00 time: 0.2564 data_time: 0.0104 memory: 13708 grad_norm: 4.6157 loss: 1.3035 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3035 2023/02/18 01:54:48 - mmengine - INFO - Epoch(train) [28][ 980/1320] lr: 2.0000e-03 eta: 2:05:54 time: 0.2557 data_time: 0.0112 memory: 13708 grad_norm: 4.5342 loss: 1.5367 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.5367 2023/02/18 01:54:53 - mmengine - INFO - Epoch(train) [28][1000/1320] lr: 2.0000e-03 eta: 2:05:49 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.6041 loss: 1.2639 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2639 2023/02/18 01:54:58 - mmengine - INFO - Epoch(train) [28][1020/1320] lr: 2.0000e-03 eta: 2:05:44 time: 0.2570 data_time: 0.0127 memory: 13708 grad_norm: 4.6612 loss: 1.2681 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2681 2023/02/18 01:55:03 - mmengine - INFO - Epoch(train) [28][1040/1320] lr: 2.0000e-03 eta: 2:05:39 time: 0.2558 data_time: 0.0111 memory: 13708 grad_norm: 4.5843 loss: 1.3490 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3490 2023/02/18 01:55:08 - mmengine - INFO - Epoch(train) [28][1060/1320] lr: 2.0000e-03 eta: 2:05:34 time: 0.2587 data_time: 0.0133 memory: 13708 grad_norm: 4.4729 loss: 1.3551 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3551 2023/02/18 01:55:13 - mmengine - INFO - Epoch(train) [28][1080/1320] lr: 2.0000e-03 eta: 2:05:29 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.6886 loss: 1.3420 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.3420 2023/02/18 01:55:18 - mmengine - INFO - Epoch(train) [28][1100/1320] lr: 2.0000e-03 eta: 2:05:23 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 4.7114 loss: 1.4208 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.4208 2023/02/18 01:55:23 - mmengine - INFO - Epoch(train) [28][1120/1320] lr: 2.0000e-03 eta: 2:05:18 time: 0.2575 data_time: 0.0130 memory: 13708 grad_norm: 4.6530 loss: 1.4016 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.4016 2023/02/18 01:55:29 - mmengine - INFO - Epoch(train) [28][1140/1320] lr: 2.0000e-03 eta: 2:05:13 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 4.6282 loss: 1.3361 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3361 2023/02/18 01:55:34 - mmengine - INFO - Epoch(train) [28][1160/1320] lr: 2.0000e-03 eta: 2:05:08 time: 0.2549 data_time: 0.0109 memory: 13708 grad_norm: 4.5504 loss: 1.3334 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3334 2023/02/18 01:55:39 - mmengine - INFO - Epoch(train) [28][1180/1320] lr: 2.0000e-03 eta: 2:05:03 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.7896 loss: 1.5171 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.5171 2023/02/18 01:55:44 - mmengine - INFO - Epoch(train) [28][1200/1320] lr: 2.0000e-03 eta: 2:04:58 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.6543 loss: 1.3678 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3678 2023/02/18 01:55:49 - mmengine - INFO - Epoch(train) [28][1220/1320] lr: 2.0000e-03 eta: 2:04:52 time: 0.2560 data_time: 0.0103 memory: 13708 grad_norm: 4.6012 loss: 1.4563 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.4563 2023/02/18 01:55:54 - mmengine - INFO - Epoch(train) [28][1240/1320] lr: 2.0000e-03 eta: 2:04:47 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 4.6476 loss: 1.4506 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 1.4506 2023/02/18 01:55:59 - mmengine - INFO - Epoch(train) [28][1260/1320] lr: 2.0000e-03 eta: 2:04:42 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 4.6602 loss: 1.2831 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2831 2023/02/18 01:56:04 - mmengine - INFO - Epoch(train) [28][1280/1320] lr: 2.0000e-03 eta: 2:04:37 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.7276 loss: 1.3420 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3420 2023/02/18 01:56:09 - mmengine - INFO - Epoch(train) [28][1300/1320] lr: 2.0000e-03 eta: 2:04:32 time: 0.2557 data_time: 0.0112 memory: 13708 grad_norm: 4.6994 loss: 1.2127 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2127 2023/02/18 01:56:14 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:56:14 - mmengine - INFO - Epoch(train) [28][1320/1320] lr: 2.0000e-03 eta: 2:04:27 time: 0.2509 data_time: 0.0100 memory: 13708 grad_norm: 4.5665 loss: 1.3810 top1_acc: 0.7273 top5_acc: 0.9091 loss_cls: 1.3810 2023/02/18 01:56:17 - mmengine - INFO - Epoch(val) [28][ 20/194] eta: 0:00:21 time: 0.1257 data_time: 0.0574 memory: 1818 2023/02/18 01:56:19 - mmengine - INFO - Epoch(val) [28][ 40/194] eta: 0:00:16 time: 0.0855 data_time: 0.0172 memory: 1818 2023/02/18 01:56:21 - mmengine - INFO - Epoch(val) [28][ 60/194] eta: 0:00:13 time: 0.0893 data_time: 0.0205 memory: 1818 2023/02/18 01:56:22 - mmengine - INFO - Epoch(val) [28][ 80/194] eta: 0:00:10 time: 0.0837 data_time: 0.0158 memory: 1818 2023/02/18 01:56:24 - mmengine - INFO - Epoch(val) [28][100/194] eta: 0:00:08 time: 0.0933 data_time: 0.0252 memory: 1818 2023/02/18 01:56:26 - mmengine - INFO - Epoch(val) [28][120/194] eta: 0:00:06 time: 0.0874 data_time: 0.0196 memory: 1818 2023/02/18 01:56:28 - mmengine - INFO - Epoch(val) [28][140/194] eta: 0:00:05 time: 0.0922 data_time: 0.0240 memory: 1818 2023/02/18 01:56:29 - mmengine - INFO - Epoch(val) [28][160/194] eta: 0:00:03 time: 0.0819 data_time: 0.0126 memory: 1818 2023/02/18 01:56:31 - mmengine - INFO - Epoch(val) [28][180/194] eta: 0:00:01 time: 0.0929 data_time: 0.0244 memory: 1818 2023/02/18 01:56:33 - mmengine - INFO - Epoch(val) [28][194/194] acc/top1: 0.5793 acc/top5: 0.8434 acc/mean1: 0.5075 2023/02/18 01:56:33 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_27.pth is removed 2023/02/18 01:56:34 - mmengine - INFO - The best checkpoint with 0.5793 acc/top1 at 28 epoch is saved to best_acc/top1_epoch_28.pth. 2023/02/18 01:56:40 - mmengine - INFO - Epoch(train) [29][ 20/1320] lr: 2.0000e-03 eta: 2:04:22 time: 0.2898 data_time: 0.0379 memory: 13708 grad_norm: 4.6229 loss: 1.3197 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.3197 2023/02/18 01:56:45 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 01:56:45 - mmengine - INFO - Epoch(train) [29][ 40/1320] lr: 2.0000e-03 eta: 2:04:17 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 4.6379 loss: 1.4758 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.4758 2023/02/18 01:56:50 - mmengine - INFO - Epoch(train) [29][ 60/1320] lr: 2.0000e-03 eta: 2:04:12 time: 0.2553 data_time: 0.0105 memory: 13708 grad_norm: 4.5517 loss: 1.2539 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2539 2023/02/18 01:56:55 - mmengine - INFO - Epoch(train) [29][ 80/1320] lr: 2.0000e-03 eta: 2:04:06 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 4.4584 loss: 1.2296 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2296 2023/02/18 01:57:00 - mmengine - INFO - Epoch(train) [29][ 100/1320] lr: 2.0000e-03 eta: 2:04:01 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.5353 loss: 1.2504 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2504 2023/02/18 01:57:05 - mmengine - INFO - Epoch(train) [29][ 120/1320] lr: 2.0000e-03 eta: 2:03:56 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.6654 loss: 1.2918 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2918 2023/02/18 01:57:10 - mmengine - INFO - Epoch(train) [29][ 140/1320] lr: 2.0000e-03 eta: 2:03:51 time: 0.2555 data_time: 0.0103 memory: 13708 grad_norm: 4.6099 loss: 1.2737 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2737 2023/02/18 01:57:16 - mmengine - INFO - Epoch(train) [29][ 160/1320] lr: 2.0000e-03 eta: 2:03:46 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.5357 loss: 1.2850 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2850 2023/02/18 01:57:21 - mmengine - INFO - Epoch(train) [29][ 180/1320] lr: 2.0000e-03 eta: 2:03:41 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 4.7263 loss: 1.3067 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.3067 2023/02/18 01:57:26 - mmengine - INFO - Epoch(train) [29][ 200/1320] lr: 2.0000e-03 eta: 2:03:35 time: 0.2560 data_time: 0.0111 memory: 13708 grad_norm: 4.6141 loss: 1.2743 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2743 2023/02/18 01:57:31 - mmengine - INFO - Epoch(train) [29][ 220/1320] lr: 2.0000e-03 eta: 2:03:30 time: 0.2554 data_time: 0.0105 memory: 13708 grad_norm: 4.6800 loss: 1.1944 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1944 2023/02/18 01:57:36 - mmengine - INFO - Epoch(train) [29][ 240/1320] lr: 2.0000e-03 eta: 2:03:25 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 4.6193 loss: 1.4440 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4440 2023/02/18 01:57:41 - mmengine - INFO - Epoch(train) [29][ 260/1320] lr: 2.0000e-03 eta: 2:03:20 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.5713 loss: 1.2343 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2343 2023/02/18 01:57:46 - mmengine - INFO - Epoch(train) [29][ 280/1320] lr: 2.0000e-03 eta: 2:03:15 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 4.7146 loss: 1.4068 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.4068 2023/02/18 01:57:51 - mmengine - INFO - Epoch(train) [29][ 300/1320] lr: 2.0000e-03 eta: 2:03:10 time: 0.2554 data_time: 0.0111 memory: 13708 grad_norm: 4.7282 loss: 1.2789 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2789 2023/02/18 01:57:56 - mmengine - INFO - Epoch(train) [29][ 320/1320] lr: 2.0000e-03 eta: 2:03:04 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 4.6798 loss: 1.3029 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.3029 2023/02/18 01:58:02 - mmengine - INFO - Epoch(train) [29][ 340/1320] lr: 2.0000e-03 eta: 2:02:59 time: 0.2580 data_time: 0.0120 memory: 13708 grad_norm: 4.5431 loss: 1.2939 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2939 2023/02/18 01:58:07 - mmengine - INFO - Epoch(train) [29][ 360/1320] lr: 2.0000e-03 eta: 2:02:54 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.4980 loss: 1.1414 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1414 2023/02/18 01:58:12 - mmengine - INFO - Epoch(train) [29][ 380/1320] lr: 2.0000e-03 eta: 2:02:49 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 4.5901 loss: 1.3307 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3307 2023/02/18 01:58:17 - mmengine - INFO - Epoch(train) [29][ 400/1320] lr: 2.0000e-03 eta: 2:02:44 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 4.8277 loss: 1.3297 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3297 2023/02/18 01:58:22 - mmengine - INFO - Epoch(train) [29][ 420/1320] lr: 2.0000e-03 eta: 2:02:39 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 4.5504 loss: 1.2342 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2342 2023/02/18 01:58:27 - mmengine - INFO - Epoch(train) [29][ 440/1320] lr: 2.0000e-03 eta: 2:02:33 time: 0.2566 data_time: 0.0108 memory: 13708 grad_norm: 4.5569 loss: 1.2591 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2591 2023/02/18 01:58:32 - mmengine - INFO - Epoch(train) [29][ 460/1320] lr: 2.0000e-03 eta: 2:02:28 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 4.6098 loss: 1.5555 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 1.5555 2023/02/18 01:58:37 - mmengine - INFO - Epoch(train) [29][ 480/1320] lr: 2.0000e-03 eta: 2:02:23 time: 0.2550 data_time: 0.0107 memory: 13708 grad_norm: 4.5887 loss: 1.2052 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2052 2023/02/18 01:58:43 - mmengine - INFO - Epoch(train) [29][ 500/1320] lr: 2.0000e-03 eta: 2:02:18 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 4.6562 loss: 1.1537 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1537 2023/02/18 01:58:48 - mmengine - INFO - Epoch(train) [29][ 520/1320] lr: 2.0000e-03 eta: 2:02:13 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 4.7493 loss: 1.3476 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3476 2023/02/18 01:58:53 - mmengine - INFO - Epoch(train) [29][ 540/1320] lr: 2.0000e-03 eta: 2:02:08 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 4.7207 loss: 1.3769 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3769 2023/02/18 01:58:58 - mmengine - INFO - Epoch(train) [29][ 560/1320] lr: 2.0000e-03 eta: 2:02:02 time: 0.2563 data_time: 0.0113 memory: 13708 grad_norm: 4.6947 loss: 1.2040 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2040 2023/02/18 01:59:03 - mmengine - INFO - Epoch(train) [29][ 580/1320] lr: 2.0000e-03 eta: 2:01:57 time: 0.2560 data_time: 0.0112 memory: 13708 grad_norm: 4.5809 loss: 1.2120 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.2120 2023/02/18 01:59:08 - mmengine - INFO - Epoch(train) [29][ 600/1320] lr: 2.0000e-03 eta: 2:01:52 time: 0.2549 data_time: 0.0104 memory: 13708 grad_norm: 4.6824 loss: 1.3626 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3626 2023/02/18 01:59:13 - mmengine - INFO - Epoch(train) [29][ 620/1320] lr: 2.0000e-03 eta: 2:01:47 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 4.6659 loss: 1.2393 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.2393 2023/02/18 01:59:18 - mmengine - INFO - Epoch(train) [29][ 640/1320] lr: 2.0000e-03 eta: 2:01:42 time: 0.2574 data_time: 0.0118 memory: 13708 grad_norm: 4.8211 loss: 1.5232 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.5232 2023/02/18 01:59:24 - mmengine - INFO - Epoch(train) [29][ 660/1320] lr: 2.0000e-03 eta: 2:01:37 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.7821 loss: 1.2470 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2470 2023/02/18 01:59:29 - mmengine - INFO - Epoch(train) [29][ 680/1320] lr: 2.0000e-03 eta: 2:01:32 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 4.7939 loss: 1.3188 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3188 2023/02/18 01:59:34 - mmengine - INFO - Epoch(train) [29][ 700/1320] lr: 2.0000e-03 eta: 2:01:26 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 4.4928 loss: 1.2487 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2487 2023/02/18 01:59:39 - mmengine - INFO - Epoch(train) [29][ 720/1320] lr: 2.0000e-03 eta: 2:01:21 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 4.7029 loss: 1.1932 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.1932 2023/02/18 01:59:44 - mmengine - INFO - Epoch(train) [29][ 740/1320] lr: 2.0000e-03 eta: 2:01:16 time: 0.2564 data_time: 0.0108 memory: 13708 grad_norm: 4.7629 loss: 1.5758 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.5758 2023/02/18 01:59:49 - mmengine - INFO - Epoch(train) [29][ 760/1320] lr: 2.0000e-03 eta: 2:01:11 time: 0.2560 data_time: 0.0105 memory: 13708 grad_norm: 4.5650 loss: 1.3074 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3074 2023/02/18 01:59:54 - mmengine - INFO - Epoch(train) [29][ 780/1320] lr: 2.0000e-03 eta: 2:01:06 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 4.6822 loss: 1.2908 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2908 2023/02/18 01:59:59 - mmengine - INFO - Epoch(train) [29][ 800/1320] lr: 2.0000e-03 eta: 2:01:01 time: 0.2549 data_time: 0.0107 memory: 13708 grad_norm: 4.7398 loss: 1.3107 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3107 2023/02/18 02:00:04 - mmengine - INFO - Epoch(train) [29][ 820/1320] lr: 2.0000e-03 eta: 2:00:55 time: 0.2550 data_time: 0.0104 memory: 13708 grad_norm: 4.6979 loss: 1.3874 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3874 2023/02/18 02:00:10 - mmengine - INFO - Epoch(train) [29][ 840/1320] lr: 2.0000e-03 eta: 2:00:50 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.8092 loss: 1.5013 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.5013 2023/02/18 02:00:15 - mmengine - INFO - Epoch(train) [29][ 860/1320] lr: 2.0000e-03 eta: 2:00:45 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.6645 loss: 1.1048 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1048 2023/02/18 02:00:20 - mmengine - INFO - Epoch(train) [29][ 880/1320] lr: 2.0000e-03 eta: 2:00:40 time: 0.2549 data_time: 0.0102 memory: 13708 grad_norm: 4.8219 loss: 1.3161 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.3161 2023/02/18 02:00:25 - mmengine - INFO - Epoch(train) [29][ 900/1320] lr: 2.0000e-03 eta: 2:00:35 time: 0.2545 data_time: 0.0100 memory: 13708 grad_norm: 4.6724 loss: 1.3985 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3985 2023/02/18 02:00:30 - mmengine - INFO - Epoch(train) [29][ 920/1320] lr: 2.0000e-03 eta: 2:00:29 time: 0.2551 data_time: 0.0103 memory: 13708 grad_norm: 4.7495 loss: 1.1478 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1478 2023/02/18 02:00:35 - mmengine - INFO - Epoch(train) [29][ 940/1320] lr: 2.0000e-03 eta: 2:00:24 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 4.6687 loss: 1.2907 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2907 2023/02/18 02:00:40 - mmengine - INFO - Epoch(train) [29][ 960/1320] lr: 2.0000e-03 eta: 2:00:19 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 4.6819 loss: 1.3338 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3338 2023/02/18 02:00:45 - mmengine - INFO - Epoch(train) [29][ 980/1320] lr: 2.0000e-03 eta: 2:00:14 time: 0.2568 data_time: 0.0126 memory: 13708 grad_norm: 4.7443 loss: 1.4407 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.4407 2023/02/18 02:00:50 - mmengine - INFO - Epoch(train) [29][1000/1320] lr: 2.0000e-03 eta: 2:00:09 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.8392 loss: 1.2613 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2613 2023/02/18 02:00:56 - mmengine - INFO - Epoch(train) [29][1020/1320] lr: 2.0000e-03 eta: 2:00:04 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 4.8630 loss: 1.2454 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2454 2023/02/18 02:01:01 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:01:01 - mmengine - INFO - Epoch(train) [29][1040/1320] lr: 2.0000e-03 eta: 1:59:58 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 4.8466 loss: 1.2418 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2418 2023/02/18 02:01:06 - mmengine - INFO - Epoch(train) [29][1060/1320] lr: 2.0000e-03 eta: 1:59:53 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.7774 loss: 1.3797 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.3797 2023/02/18 02:01:11 - mmengine - INFO - Epoch(train) [29][1080/1320] lr: 2.0000e-03 eta: 1:59:48 time: 0.2579 data_time: 0.0126 memory: 13708 grad_norm: 4.9100 loss: 1.3953 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.3953 2023/02/18 02:01:16 - mmengine - INFO - Epoch(train) [29][1100/1320] lr: 2.0000e-03 eta: 1:59:43 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 4.8818 loss: 1.4563 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4563 2023/02/18 02:01:21 - mmengine - INFO - Epoch(train) [29][1120/1320] lr: 2.0000e-03 eta: 1:59:38 time: 0.2549 data_time: 0.0103 memory: 13708 grad_norm: 4.7613 loss: 1.2643 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.2643 2023/02/18 02:01:26 - mmengine - INFO - Epoch(train) [29][1140/1320] lr: 2.0000e-03 eta: 1:59:33 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 4.8615 loss: 1.2581 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.2581 2023/02/18 02:01:31 - mmengine - INFO - Epoch(train) [29][1160/1320] lr: 2.0000e-03 eta: 1:59:28 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 4.7322 loss: 1.1650 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1650 2023/02/18 02:01:37 - mmengine - INFO - Epoch(train) [29][1180/1320] lr: 2.0000e-03 eta: 1:59:22 time: 0.2554 data_time: 0.0102 memory: 13708 grad_norm: 4.6787 loss: 1.3310 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3310 2023/02/18 02:01:42 - mmengine - INFO - Epoch(train) [29][1200/1320] lr: 2.0000e-03 eta: 1:59:17 time: 0.2565 data_time: 0.0113 memory: 13708 grad_norm: 4.8116 loss: 1.2712 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.2712 2023/02/18 02:01:47 - mmengine - INFO - Epoch(train) [29][1220/1320] lr: 2.0000e-03 eta: 1:59:12 time: 0.2563 data_time: 0.0114 memory: 13708 grad_norm: 4.7496 loss: 1.3223 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3223 2023/02/18 02:01:52 - mmengine - INFO - Epoch(train) [29][1240/1320] lr: 2.0000e-03 eta: 1:59:07 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 4.7537 loss: 1.2426 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2426 2023/02/18 02:01:57 - mmengine - INFO - Epoch(train) [29][1260/1320] lr: 2.0000e-03 eta: 1:59:02 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 4.8990 loss: 1.3548 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3548 2023/02/18 02:02:02 - mmengine - INFO - Epoch(train) [29][1280/1320] lr: 2.0000e-03 eta: 1:58:57 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.8104 loss: 1.3449 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3449 2023/02/18 02:02:07 - mmengine - INFO - Epoch(train) [29][1300/1320] lr: 2.0000e-03 eta: 1:58:51 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 4.7322 loss: 1.2828 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2828 2023/02/18 02:02:12 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:02:12 - mmengine - INFO - Epoch(train) [29][1320/1320] lr: 2.0000e-03 eta: 1:58:46 time: 0.2516 data_time: 0.0105 memory: 13708 grad_norm: 4.7139 loss: 1.3419 top1_acc: 0.6364 top5_acc: 0.8182 loss_cls: 1.3419 2023/02/18 02:02:15 - mmengine - INFO - Epoch(val) [29][ 20/194] eta: 0:00:21 time: 0.1255 data_time: 0.0575 memory: 1818 2023/02/18 02:02:17 - mmengine - INFO - Epoch(val) [29][ 40/194] eta: 0:00:16 time: 0.0868 data_time: 0.0185 memory: 1818 2023/02/18 02:02:18 - mmengine - INFO - Epoch(val) [29][ 60/194] eta: 0:00:13 time: 0.0884 data_time: 0.0201 memory: 1818 2023/02/18 02:02:20 - mmengine - INFO - Epoch(val) [29][ 80/194] eta: 0:00:10 time: 0.0848 data_time: 0.0154 memory: 1818 2023/02/18 02:02:22 - mmengine - INFO - Epoch(val) [29][100/194] eta: 0:00:08 time: 0.0893 data_time: 0.0207 memory: 1818 2023/02/18 02:02:23 - mmengine - INFO - Epoch(val) [29][120/194] eta: 0:00:06 time: 0.0840 data_time: 0.0158 memory: 1818 2023/02/18 02:02:25 - mmengine - INFO - Epoch(val) [29][140/194] eta: 0:00:05 time: 0.0906 data_time: 0.0217 memory: 1818 2023/02/18 02:02:27 - mmengine - INFO - Epoch(val) [29][160/194] eta: 0:00:03 time: 0.0827 data_time: 0.0139 memory: 1818 2023/02/18 02:02:29 - mmengine - INFO - Epoch(val) [29][180/194] eta: 0:00:01 time: 0.0929 data_time: 0.0250 memory: 1818 2023/02/18 02:02:31 - mmengine - INFO - Epoch(val) [29][194/194] acc/top1: 0.5830 acc/top5: 0.8472 acc/mean1: 0.5158 2023/02/18 02:02:31 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_28.pth is removed 2023/02/18 02:02:32 - mmengine - INFO - The best checkpoint with 0.5830 acc/top1 at 29 epoch is saved to best_acc/top1_epoch_29.pth. 2023/02/18 02:02:37 - mmengine - INFO - Epoch(train) [30][ 20/1320] lr: 2.0000e-03 eta: 1:58:42 time: 0.2887 data_time: 0.0372 memory: 13708 grad_norm: 4.7413 loss: 1.3302 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3302 2023/02/18 02:02:43 - mmengine - INFO - Epoch(train) [30][ 40/1320] lr: 2.0000e-03 eta: 1:58:36 time: 0.2564 data_time: 0.0105 memory: 13708 grad_norm: 4.6686 loss: 1.2239 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.2239 2023/02/18 02:02:48 - mmengine - INFO - Epoch(train) [30][ 60/1320] lr: 2.0000e-03 eta: 1:58:31 time: 0.2545 data_time: 0.0104 memory: 13708 grad_norm: 4.5631 loss: 1.2063 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.2063 2023/02/18 02:02:53 - mmengine - INFO - Epoch(train) [30][ 80/1320] lr: 2.0000e-03 eta: 1:58:26 time: 0.2569 data_time: 0.0117 memory: 13708 grad_norm: 4.6449 loss: 1.2373 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.2373 2023/02/18 02:02:58 - mmengine - INFO - Epoch(train) [30][ 100/1320] lr: 2.0000e-03 eta: 1:58:21 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.7309 loss: 1.3060 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3060 2023/02/18 02:03:03 - mmengine - INFO - Epoch(train) [30][ 120/1320] lr: 2.0000e-03 eta: 1:58:16 time: 0.2570 data_time: 0.0123 memory: 13708 grad_norm: 4.8269 loss: 1.2949 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2949 2023/02/18 02:03:08 - mmengine - INFO - Epoch(train) [30][ 140/1320] lr: 2.0000e-03 eta: 1:58:11 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.7658 loss: 1.1596 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1596 2023/02/18 02:03:13 - mmengine - INFO - Epoch(train) [30][ 160/1320] lr: 2.0000e-03 eta: 1:58:05 time: 0.2564 data_time: 0.0107 memory: 13708 grad_norm: 4.6186 loss: 1.1342 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1342 2023/02/18 02:03:18 - mmengine - INFO - Epoch(train) [30][ 180/1320] lr: 2.0000e-03 eta: 1:58:00 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.7033 loss: 1.3502 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3502 2023/02/18 02:03:23 - mmengine - INFO - Epoch(train) [30][ 200/1320] lr: 2.0000e-03 eta: 1:57:55 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 4.7184 loss: 1.3140 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3140 2023/02/18 02:03:29 - mmengine - INFO - Epoch(train) [30][ 220/1320] lr: 2.0000e-03 eta: 1:57:50 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 4.7281 loss: 1.4071 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.4071 2023/02/18 02:03:34 - mmengine - INFO - Epoch(train) [30][ 240/1320] lr: 2.0000e-03 eta: 1:57:45 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 4.6338 loss: 1.1997 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.1997 2023/02/18 02:03:39 - mmengine - INFO - Epoch(train) [30][ 260/1320] lr: 2.0000e-03 eta: 1:57:40 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 4.7289 loss: 1.2301 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.2301 2023/02/18 02:03:44 - mmengine - INFO - Epoch(train) [30][ 280/1320] lr: 2.0000e-03 eta: 1:57:34 time: 0.2590 data_time: 0.0129 memory: 13708 grad_norm: 4.7514 loss: 1.2168 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2168 2023/02/18 02:03:49 - mmengine - INFO - Epoch(train) [30][ 300/1320] lr: 2.0000e-03 eta: 1:57:29 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 4.7934 loss: 1.2242 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2242 2023/02/18 02:03:54 - mmengine - INFO - Epoch(train) [30][ 320/1320] lr: 2.0000e-03 eta: 1:57:24 time: 0.2558 data_time: 0.0113 memory: 13708 grad_norm: 4.8193 loss: 1.3178 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.3178 2023/02/18 02:03:59 - mmengine - INFO - Epoch(train) [30][ 340/1320] lr: 2.0000e-03 eta: 1:57:19 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.7826 loss: 1.2529 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2529 2023/02/18 02:04:04 - mmengine - INFO - Epoch(train) [30][ 360/1320] lr: 2.0000e-03 eta: 1:57:14 time: 0.2553 data_time: 0.0108 memory: 13708 grad_norm: 4.8505 loss: 1.2605 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2605 2023/02/18 02:04:10 - mmengine - INFO - Epoch(train) [30][ 380/1320] lr: 2.0000e-03 eta: 1:57:09 time: 0.2549 data_time: 0.0106 memory: 13708 grad_norm: 4.7654 loss: 1.1553 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1553 2023/02/18 02:04:15 - mmengine - INFO - Epoch(train) [30][ 400/1320] lr: 2.0000e-03 eta: 1:57:03 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.9111 loss: 1.2680 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2680 2023/02/18 02:04:20 - mmengine - INFO - Epoch(train) [30][ 420/1320] lr: 2.0000e-03 eta: 1:56:58 time: 0.2555 data_time: 0.0110 memory: 13708 grad_norm: 4.7563 loss: 1.2593 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2593 2023/02/18 02:04:25 - mmengine - INFO - Epoch(train) [30][ 440/1320] lr: 2.0000e-03 eta: 1:56:53 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.7088 loss: 1.0142 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0142 2023/02/18 02:04:30 - mmengine - INFO - Epoch(train) [30][ 460/1320] lr: 2.0000e-03 eta: 1:56:48 time: 0.2569 data_time: 0.0126 memory: 13708 grad_norm: 4.7852 loss: 1.2224 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2224 2023/02/18 02:04:35 - mmengine - INFO - Epoch(train) [30][ 480/1320] lr: 2.0000e-03 eta: 1:56:43 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 4.8724 loss: 1.2666 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2666 2023/02/18 02:04:40 - mmengine - INFO - Epoch(train) [30][ 500/1320] lr: 2.0000e-03 eta: 1:56:38 time: 0.2559 data_time: 0.0103 memory: 13708 grad_norm: 4.8471 loss: 1.2767 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2767 2023/02/18 02:04:45 - mmengine - INFO - Epoch(train) [30][ 520/1320] lr: 2.0000e-03 eta: 1:56:33 time: 0.2564 data_time: 0.0113 memory: 13708 grad_norm: 4.8564 loss: 1.2110 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2110 2023/02/18 02:04:51 - mmengine - INFO - Epoch(train) [30][ 540/1320] lr: 2.0000e-03 eta: 1:56:27 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 4.9107 loss: 1.4067 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.4067 2023/02/18 02:04:56 - mmengine - INFO - Epoch(train) [30][ 560/1320] lr: 2.0000e-03 eta: 1:56:22 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 4.8928 loss: 1.2769 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2769 2023/02/18 02:05:01 - mmengine - INFO - Epoch(train) [30][ 580/1320] lr: 2.0000e-03 eta: 1:56:17 time: 0.2562 data_time: 0.0110 memory: 13708 grad_norm: 4.7758 loss: 1.3237 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3237 2023/02/18 02:05:06 - mmengine - INFO - Epoch(train) [30][ 600/1320] lr: 2.0000e-03 eta: 1:56:12 time: 0.2552 data_time: 0.0100 memory: 13708 grad_norm: 4.8159 loss: 1.2530 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.2530 2023/02/18 02:05:11 - mmengine - INFO - Epoch(train) [30][ 620/1320] lr: 2.0000e-03 eta: 1:56:07 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 4.9423 loss: 1.3738 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3738 2023/02/18 02:05:16 - mmengine - INFO - Epoch(train) [30][ 640/1320] lr: 2.0000e-03 eta: 1:56:02 time: 0.2582 data_time: 0.0132 memory: 13708 grad_norm: 4.7705 loss: 1.1731 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1731 2023/02/18 02:05:21 - mmengine - INFO - Epoch(train) [30][ 660/1320] lr: 2.0000e-03 eta: 1:55:56 time: 0.2555 data_time: 0.0103 memory: 13708 grad_norm: 4.8812 loss: 1.3515 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.3515 2023/02/18 02:05:26 - mmengine - INFO - Epoch(train) [30][ 680/1320] lr: 2.0000e-03 eta: 1:55:51 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 4.7181 loss: 1.4030 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.4030 2023/02/18 02:05:32 - mmengine - INFO - Epoch(train) [30][ 700/1320] lr: 2.0000e-03 eta: 1:55:46 time: 0.2557 data_time: 0.0111 memory: 13708 grad_norm: 4.8859 loss: 1.2686 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2686 2023/02/18 02:05:37 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:05:37 - mmengine - INFO - Epoch(train) [30][ 720/1320] lr: 2.0000e-03 eta: 1:55:41 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 4.7713 loss: 1.2703 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2703 2023/02/18 02:05:42 - mmengine - INFO - Epoch(train) [30][ 740/1320] lr: 2.0000e-03 eta: 1:55:36 time: 0.2560 data_time: 0.0106 memory: 13708 grad_norm: 4.8593 loss: 1.1423 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1423 2023/02/18 02:05:47 - mmengine - INFO - Epoch(train) [30][ 760/1320] lr: 2.0000e-03 eta: 1:55:31 time: 0.2553 data_time: 0.0104 memory: 13708 grad_norm: 4.8082 loss: 1.3690 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.3690 2023/02/18 02:05:52 - mmengine - INFO - Epoch(train) [30][ 780/1320] lr: 2.0000e-03 eta: 1:55:25 time: 0.2574 data_time: 0.0126 memory: 13708 grad_norm: 4.8462 loss: 1.0002 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0002 2023/02/18 02:05:57 - mmengine - INFO - Epoch(train) [30][ 800/1320] lr: 2.0000e-03 eta: 1:55:20 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 4.7491 loss: 1.1753 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1753 2023/02/18 02:06:02 - mmengine - INFO - Epoch(train) [30][ 820/1320] lr: 2.0000e-03 eta: 1:55:15 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 4.9836 loss: 1.3801 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3801 2023/02/18 02:06:07 - mmengine - INFO - Epoch(train) [30][ 840/1320] lr: 2.0000e-03 eta: 1:55:10 time: 0.2563 data_time: 0.0112 memory: 13708 grad_norm: 4.8824 loss: 1.3007 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.3007 2023/02/18 02:06:12 - mmengine - INFO - Epoch(train) [30][ 860/1320] lr: 2.0000e-03 eta: 1:55:05 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.7952 loss: 1.1832 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1832 2023/02/18 02:06:18 - mmengine - INFO - Epoch(train) [30][ 880/1320] lr: 2.0000e-03 eta: 1:55:00 time: 0.2552 data_time: 0.0104 memory: 13708 grad_norm: 4.8449 loss: 1.3604 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3604 2023/02/18 02:06:23 - mmengine - INFO - Epoch(train) [30][ 900/1320] lr: 2.0000e-03 eta: 1:54:55 time: 0.2563 data_time: 0.0112 memory: 13708 grad_norm: 4.8856 loss: 1.2725 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2725 2023/02/18 02:06:28 - mmengine - INFO - Epoch(train) [30][ 920/1320] lr: 2.0000e-03 eta: 1:54:49 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 4.9577 loss: 1.1838 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1838 2023/02/18 02:06:33 - mmengine - INFO - Epoch(train) [30][ 940/1320] lr: 2.0000e-03 eta: 1:54:44 time: 0.2553 data_time: 0.0109 memory: 13708 grad_norm: 4.9140 loss: 1.3547 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3547 2023/02/18 02:06:38 - mmengine - INFO - Epoch(train) [30][ 960/1320] lr: 2.0000e-03 eta: 1:54:39 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 4.9620 loss: 1.3074 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3074 2023/02/18 02:06:43 - mmengine - INFO - Epoch(train) [30][ 980/1320] lr: 2.0000e-03 eta: 1:54:34 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 4.9274 loss: 1.2605 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2605 2023/02/18 02:06:48 - mmengine - INFO - Epoch(train) [30][1000/1320] lr: 2.0000e-03 eta: 1:54:29 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 5.1037 loss: 1.4138 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.4138 2023/02/18 02:06:53 - mmengine - INFO - Epoch(train) [30][1020/1320] lr: 2.0000e-03 eta: 1:54:24 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 4.8912 loss: 1.2431 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2431 2023/02/18 02:06:59 - mmengine - INFO - Epoch(train) [30][1040/1320] lr: 2.0000e-03 eta: 1:54:18 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 4.9421 loss: 1.2379 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2379 2023/02/18 02:07:04 - mmengine - INFO - Epoch(train) [30][1060/1320] lr: 2.0000e-03 eta: 1:54:13 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 4.9799 loss: 1.2374 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2374 2023/02/18 02:07:09 - mmengine - INFO - Epoch(train) [30][1080/1320] lr: 2.0000e-03 eta: 1:54:08 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 4.9217 loss: 1.1796 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1796 2023/02/18 02:07:14 - mmengine - INFO - Epoch(train) [30][1100/1320] lr: 2.0000e-03 eta: 1:54:03 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 4.9792 loss: 1.2915 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.2915 2023/02/18 02:07:19 - mmengine - INFO - Epoch(train) [30][1120/1320] lr: 2.0000e-03 eta: 1:53:58 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 4.8524 loss: 1.3227 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3227 2023/02/18 02:07:24 - mmengine - INFO - Epoch(train) [30][1140/1320] lr: 2.0000e-03 eta: 1:53:53 time: 0.2550 data_time: 0.0100 memory: 13708 grad_norm: 4.9201 loss: 1.2353 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2353 2023/02/18 02:07:29 - mmengine - INFO - Epoch(train) [30][1160/1320] lr: 2.0000e-03 eta: 1:53:47 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 4.9282 loss: 1.3797 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3797 2023/02/18 02:07:34 - mmengine - INFO - Epoch(train) [30][1180/1320] lr: 2.0000e-03 eta: 1:53:42 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 5.0224 loss: 1.2806 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2806 2023/02/18 02:07:39 - mmengine - INFO - Epoch(train) [30][1200/1320] lr: 2.0000e-03 eta: 1:53:37 time: 0.2558 data_time: 0.0105 memory: 13708 grad_norm: 4.8463 loss: 1.2564 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2564 2023/02/18 02:07:45 - mmengine - INFO - Epoch(train) [30][1220/1320] lr: 2.0000e-03 eta: 1:53:32 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 5.0374 loss: 1.2359 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2359 2023/02/18 02:07:50 - mmengine - INFO - Epoch(train) [30][1240/1320] lr: 2.0000e-03 eta: 1:53:27 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 4.7698 loss: 1.1182 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1182 2023/02/18 02:07:55 - mmengine - INFO - Epoch(train) [30][1260/1320] lr: 2.0000e-03 eta: 1:53:22 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 4.9191 loss: 1.1247 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1247 2023/02/18 02:08:00 - mmengine - INFO - Epoch(train) [30][1280/1320] lr: 2.0000e-03 eta: 1:53:16 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 4.9308 loss: 1.2449 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2449 2023/02/18 02:08:05 - mmengine - INFO - Epoch(train) [30][1300/1320] lr: 2.0000e-03 eta: 1:53:11 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 4.8159 loss: 1.2938 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2938 2023/02/18 02:08:10 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:08:10 - mmengine - INFO - Epoch(train) [30][1320/1320] lr: 2.0000e-03 eta: 1:53:06 time: 0.2510 data_time: 0.0103 memory: 13708 grad_norm: 4.9921 loss: 1.1788 top1_acc: 0.5455 top5_acc: 0.9091 loss_cls: 1.1788 2023/02/18 02:08:10 - mmengine - INFO - Saving checkpoint at 30 epochs 2023/02/18 02:08:14 - mmengine - INFO - Epoch(val) [30][ 20/194] eta: 0:00:21 time: 0.1259 data_time: 0.0568 memory: 1818 2023/02/18 02:08:15 - mmengine - INFO - Epoch(val) [30][ 40/194] eta: 0:00:16 time: 0.0874 data_time: 0.0184 memory: 1818 2023/02/18 02:08:17 - mmengine - INFO - Epoch(val) [30][ 60/194] eta: 0:00:13 time: 0.0908 data_time: 0.0225 memory: 1818 2023/02/18 02:08:19 - mmengine - INFO - Epoch(val) [30][ 80/194] eta: 0:00:11 time: 0.0850 data_time: 0.0163 memory: 1818 2023/02/18 02:08:21 - mmengine - INFO - Epoch(val) [30][100/194] eta: 0:00:09 time: 0.0897 data_time: 0.0210 memory: 1818 2023/02/18 02:08:23 - mmengine - INFO - Epoch(val) [30][120/194] eta: 0:00:06 time: 0.0852 data_time: 0.0164 memory: 1818 2023/02/18 02:08:24 - mmengine - INFO - Epoch(val) [30][140/194] eta: 0:00:05 time: 0.0896 data_time: 0.0204 memory: 1818 2023/02/18 02:08:26 - mmengine - INFO - Epoch(val) [30][160/194] eta: 0:00:03 time: 0.0825 data_time: 0.0135 memory: 1818 2023/02/18 02:08:28 - mmengine - INFO - Epoch(val) [30][180/194] eta: 0:00:01 time: 0.0799 data_time: 0.0133 memory: 1818 2023/02/18 02:08:29 - mmengine - INFO - Epoch(val) [30][194/194] acc/top1: 0.5872 acc/top5: 0.8501 acc/mean1: 0.5157 2023/02/18 02:08:29 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_29.pth is removed 2023/02/18 02:08:30 - mmengine - INFO - The best checkpoint with 0.5872 acc/top1 at 30 epoch is saved to best_acc/top1_epoch_30.pth. 2023/02/18 02:08:36 - mmengine - INFO - Epoch(train) [31][ 20/1320] lr: 2.0000e-03 eta: 1:53:01 time: 0.2922 data_time: 0.0396 memory: 13708 grad_norm: 4.8192 loss: 1.2874 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2874 2023/02/18 02:08:41 - mmengine - INFO - Epoch(train) [31][ 40/1320] lr: 2.0000e-03 eta: 1:52:56 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 4.9620 loss: 1.2958 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2958 2023/02/18 02:08:46 - mmengine - INFO - Epoch(train) [31][ 60/1320] lr: 2.0000e-03 eta: 1:52:51 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 4.7777 loss: 1.1102 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1102 2023/02/18 02:08:51 - mmengine - INFO - Epoch(train) [31][ 80/1320] lr: 2.0000e-03 eta: 1:52:46 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 4.8202 loss: 1.1348 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.1348 2023/02/18 02:08:56 - mmengine - INFO - Epoch(train) [31][ 100/1320] lr: 2.0000e-03 eta: 1:52:41 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 4.9382 loss: 1.3101 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3101 2023/02/18 02:09:02 - mmengine - INFO - Epoch(train) [31][ 120/1320] lr: 2.0000e-03 eta: 1:52:36 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.9158 loss: 1.2238 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2238 2023/02/18 02:09:07 - mmengine - INFO - Epoch(train) [31][ 140/1320] lr: 2.0000e-03 eta: 1:52:30 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 4.8767 loss: 1.1896 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1896 2023/02/18 02:09:12 - mmengine - INFO - Epoch(train) [31][ 160/1320] lr: 2.0000e-03 eta: 1:52:25 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 4.8611 loss: 1.4689 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 1.4689 2023/02/18 02:09:17 - mmengine - INFO - Epoch(train) [31][ 180/1320] lr: 2.0000e-03 eta: 1:52:20 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 4.8249 loss: 1.1313 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.1313 2023/02/18 02:09:22 - mmengine - INFO - Epoch(train) [31][ 200/1320] lr: 2.0000e-03 eta: 1:52:15 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 4.9718 loss: 1.3794 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3794 2023/02/18 02:09:27 - mmengine - INFO - Epoch(train) [31][ 220/1320] lr: 2.0000e-03 eta: 1:52:10 time: 0.2577 data_time: 0.0114 memory: 13708 grad_norm: 4.9107 loss: 1.1615 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1615 2023/02/18 02:09:32 - mmengine - INFO - Epoch(train) [31][ 240/1320] lr: 2.0000e-03 eta: 1:52:05 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.9661 loss: 1.3515 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3515 2023/02/18 02:09:37 - mmengine - INFO - Epoch(train) [31][ 260/1320] lr: 2.0000e-03 eta: 1:52:00 time: 0.2564 data_time: 0.0119 memory: 13708 grad_norm: 5.0896 loss: 1.4414 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.4414 2023/02/18 02:09:43 - mmengine - INFO - Epoch(train) [31][ 280/1320] lr: 2.0000e-03 eta: 1:51:54 time: 0.2563 data_time: 0.0104 memory: 13708 grad_norm: 5.0065 loss: 1.3033 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.3033 2023/02/18 02:09:48 - mmengine - INFO - Epoch(train) [31][ 300/1320] lr: 2.0000e-03 eta: 1:51:49 time: 0.2558 data_time: 0.0103 memory: 13708 grad_norm: 4.8881 loss: 1.2604 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2604 2023/02/18 02:09:53 - mmengine - INFO - Epoch(train) [31][ 320/1320] lr: 2.0000e-03 eta: 1:51:44 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 4.7949 loss: 1.3299 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3299 2023/02/18 02:09:58 - mmengine - INFO - Epoch(train) [31][ 340/1320] lr: 2.0000e-03 eta: 1:51:39 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 4.9180 loss: 1.0521 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 1.0521 2023/02/18 02:10:03 - mmengine - INFO - Epoch(train) [31][ 360/1320] lr: 2.0000e-03 eta: 1:51:34 time: 0.2562 data_time: 0.0113 memory: 13708 grad_norm: 4.9110 loss: 1.2938 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2938 2023/02/18 02:10:08 - mmengine - INFO - Epoch(train) [31][ 380/1320] lr: 2.0000e-03 eta: 1:51:29 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 4.9532 loss: 1.2598 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2598 2023/02/18 02:10:13 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:10:13 - mmengine - INFO - Epoch(train) [31][ 400/1320] lr: 2.0000e-03 eta: 1:51:23 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 4.9631 loss: 1.2037 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2037 2023/02/18 02:10:18 - mmengine - INFO - Epoch(train) [31][ 420/1320] lr: 2.0000e-03 eta: 1:51:18 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 4.8983 loss: 1.4173 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.4173 2023/02/18 02:10:24 - mmengine - INFO - Epoch(train) [31][ 440/1320] lr: 2.0000e-03 eta: 1:51:13 time: 0.2563 data_time: 0.0115 memory: 13708 grad_norm: 4.9453 loss: 1.1919 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1919 2023/02/18 02:10:29 - mmengine - INFO - Epoch(train) [31][ 460/1320] lr: 2.0000e-03 eta: 1:51:08 time: 0.2557 data_time: 0.0104 memory: 13708 grad_norm: 5.0729 loss: 1.1350 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1350 2023/02/18 02:10:34 - mmengine - INFO - Epoch(train) [31][ 480/1320] lr: 2.0000e-03 eta: 1:51:03 time: 0.2560 data_time: 0.0114 memory: 13708 grad_norm: 4.8602 loss: 1.2928 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2928 2023/02/18 02:10:39 - mmengine - INFO - Epoch(train) [31][ 500/1320] lr: 2.0000e-03 eta: 1:50:58 time: 0.2552 data_time: 0.0109 memory: 13708 grad_norm: 5.1619 loss: 1.2577 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2577 2023/02/18 02:10:44 - mmengine - INFO - Epoch(train) [31][ 520/1320] lr: 2.0000e-03 eta: 1:50:52 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 5.0636 loss: 1.2620 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2620 2023/02/18 02:10:49 - mmengine - INFO - Epoch(train) [31][ 540/1320] lr: 2.0000e-03 eta: 1:50:47 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 4.8671 loss: 1.1211 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1211 2023/02/18 02:10:54 - mmengine - INFO - Epoch(train) [31][ 560/1320] lr: 2.0000e-03 eta: 1:50:42 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 4.9892 loss: 1.3066 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3066 2023/02/18 02:10:59 - mmengine - INFO - Epoch(train) [31][ 580/1320] lr: 2.0000e-03 eta: 1:50:37 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 5.0026 loss: 1.2165 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2165 2023/02/18 02:11:04 - mmengine - INFO - Epoch(train) [31][ 600/1320] lr: 2.0000e-03 eta: 1:50:32 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 4.9403 loss: 1.3356 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.3356 2023/02/18 02:11:10 - mmengine - INFO - Epoch(train) [31][ 620/1320] lr: 2.0000e-03 eta: 1:50:27 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 4.8601 loss: 1.2079 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2079 2023/02/18 02:11:15 - mmengine - INFO - Epoch(train) [31][ 640/1320] lr: 2.0000e-03 eta: 1:50:22 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 4.9963 loss: 1.1828 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1828 2023/02/18 02:11:20 - mmengine - INFO - Epoch(train) [31][ 660/1320] lr: 2.0000e-03 eta: 1:50:16 time: 0.2560 data_time: 0.0114 memory: 13708 grad_norm: 4.9946 loss: 1.2587 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2587 2023/02/18 02:11:25 - mmengine - INFO - Epoch(train) [31][ 680/1320] lr: 2.0000e-03 eta: 1:50:11 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 4.9523 loss: 1.2612 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2612 2023/02/18 02:11:30 - mmengine - INFO - Epoch(train) [31][ 700/1320] lr: 2.0000e-03 eta: 1:50:06 time: 0.2569 data_time: 0.0123 memory: 13708 grad_norm: 4.7815 loss: 1.1063 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1063 2023/02/18 02:11:35 - mmengine - INFO - Epoch(train) [31][ 720/1320] lr: 2.0000e-03 eta: 1:50:01 time: 0.2551 data_time: 0.0105 memory: 13708 grad_norm: 4.9506 loss: 1.1714 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1714 2023/02/18 02:11:40 - mmengine - INFO - Epoch(train) [31][ 740/1320] lr: 2.0000e-03 eta: 1:49:56 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 5.0600 loss: 1.1766 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1766 2023/02/18 02:11:45 - mmengine - INFO - Epoch(train) [31][ 760/1320] lr: 2.0000e-03 eta: 1:49:51 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 4.9234 loss: 1.3322 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3322 2023/02/18 02:11:51 - mmengine - INFO - Epoch(train) [31][ 780/1320] lr: 2.0000e-03 eta: 1:49:45 time: 0.2552 data_time: 0.0105 memory: 13708 grad_norm: 5.1171 loss: 1.3115 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.3115 2023/02/18 02:11:56 - mmengine - INFO - Epoch(train) [31][ 800/1320] lr: 2.0000e-03 eta: 1:49:40 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 5.1005 loss: 1.2574 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.2574 2023/02/18 02:12:01 - mmengine - INFO - Epoch(train) [31][ 820/1320] lr: 2.0000e-03 eta: 1:49:35 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 5.1097 loss: 1.1615 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.1615 2023/02/18 02:12:06 - mmengine - INFO - Epoch(train) [31][ 840/1320] lr: 2.0000e-03 eta: 1:49:30 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 4.9892 loss: 1.2997 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2997 2023/02/18 02:12:11 - mmengine - INFO - Epoch(train) [31][ 860/1320] lr: 2.0000e-03 eta: 1:49:25 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 5.0394 loss: 1.2387 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2387 2023/02/18 02:12:16 - mmengine - INFO - Epoch(train) [31][ 880/1320] lr: 2.0000e-03 eta: 1:49:20 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 5.0260 loss: 1.1975 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1975 2023/02/18 02:12:21 - mmengine - INFO - Epoch(train) [31][ 900/1320] lr: 2.0000e-03 eta: 1:49:14 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 4.8472 loss: 1.2276 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.2276 2023/02/18 02:12:26 - mmengine - INFO - Epoch(train) [31][ 920/1320] lr: 2.0000e-03 eta: 1:49:09 time: 0.2569 data_time: 0.0113 memory: 13708 grad_norm: 4.9223 loss: 1.3140 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3140 2023/02/18 02:12:31 - mmengine - INFO - Epoch(train) [31][ 940/1320] lr: 2.0000e-03 eta: 1:49:04 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 4.9129 loss: 1.2140 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.2140 2023/02/18 02:12:37 - mmengine - INFO - Epoch(train) [31][ 960/1320] lr: 2.0000e-03 eta: 1:48:59 time: 0.2559 data_time: 0.0106 memory: 13708 grad_norm: 5.0240 loss: 1.3571 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3571 2023/02/18 02:12:42 - mmengine - INFO - Epoch(train) [31][ 980/1320] lr: 2.0000e-03 eta: 1:48:54 time: 0.2571 data_time: 0.0127 memory: 13708 grad_norm: 5.0168 loss: 1.0587 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.0587 2023/02/18 02:12:47 - mmengine - INFO - Epoch(train) [31][1000/1320] lr: 2.0000e-03 eta: 1:48:49 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 4.9996 loss: 1.3049 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3049 2023/02/18 02:12:52 - mmengine - INFO - Epoch(train) [31][1020/1320] lr: 2.0000e-03 eta: 1:48:44 time: 0.2559 data_time: 0.0114 memory: 13708 grad_norm: 5.0357 loss: 1.2639 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2639 2023/02/18 02:12:57 - mmengine - INFO - Epoch(train) [31][1040/1320] lr: 2.0000e-03 eta: 1:48:38 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 5.1547 loss: 1.3151 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3151 2023/02/18 02:13:02 - mmengine - INFO - Epoch(train) [31][1060/1320] lr: 2.0000e-03 eta: 1:48:33 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 5.0582 loss: 1.2359 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2359 2023/02/18 02:13:07 - mmengine - INFO - Epoch(train) [31][1080/1320] lr: 2.0000e-03 eta: 1:48:28 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 4.9351 loss: 1.2490 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2490 2023/02/18 02:13:13 - mmengine - INFO - Epoch(train) [31][1100/1320] lr: 2.0000e-03 eta: 1:48:23 time: 0.2660 data_time: 0.0208 memory: 13708 grad_norm: 5.1147 loss: 1.3912 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3912 2023/02/18 02:13:18 - mmengine - INFO - Epoch(train) [31][1120/1320] lr: 2.0000e-03 eta: 1:48:18 time: 0.2562 data_time: 0.0113 memory: 13708 grad_norm: 4.8934 loss: 1.2356 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.2356 2023/02/18 02:13:23 - mmengine - INFO - Epoch(train) [31][1140/1320] lr: 2.0000e-03 eta: 1:48:13 time: 0.2550 data_time: 0.0106 memory: 13708 grad_norm: 4.9923 loss: 1.2390 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.2390 2023/02/18 02:13:28 - mmengine - INFO - Epoch(train) [31][1160/1320] lr: 2.0000e-03 eta: 1:48:08 time: 0.2573 data_time: 0.0129 memory: 13708 grad_norm: 4.9836 loss: 1.0651 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0651 2023/02/18 02:13:33 - mmengine - INFO - Epoch(train) [31][1180/1320] lr: 2.0000e-03 eta: 1:48:02 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 5.0088 loss: 1.2511 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.2511 2023/02/18 02:13:38 - mmengine - INFO - Epoch(train) [31][1200/1320] lr: 2.0000e-03 eta: 1:47:57 time: 0.2560 data_time: 0.0104 memory: 13708 grad_norm: 5.1719 loss: 1.1377 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1377 2023/02/18 02:13:43 - mmengine - INFO - Epoch(train) [31][1220/1320] lr: 2.0000e-03 eta: 1:47:52 time: 0.2576 data_time: 0.0128 memory: 13708 grad_norm: 5.1606 loss: 1.3279 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.3279 2023/02/18 02:13:49 - mmengine - INFO - Epoch(train) [31][1240/1320] lr: 2.0000e-03 eta: 1:47:47 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 5.1639 loss: 1.2674 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2674 2023/02/18 02:13:54 - mmengine - INFO - Epoch(train) [31][1260/1320] lr: 2.0000e-03 eta: 1:47:42 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 5.1214 loss: 1.3084 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.3084 2023/02/18 02:13:59 - mmengine - INFO - Epoch(train) [31][1280/1320] lr: 2.0000e-03 eta: 1:47:37 time: 0.2557 data_time: 0.0113 memory: 13708 grad_norm: 5.0276 loss: 1.3538 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.3538 2023/02/18 02:14:04 - mmengine - INFO - Epoch(train) [31][1300/1320] lr: 2.0000e-03 eta: 1:47:32 time: 0.2587 data_time: 0.0134 memory: 13708 grad_norm: 5.1764 loss: 1.3013 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.3013 2023/02/18 02:14:09 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:14:09 - mmengine - INFO - Epoch(train) [31][1320/1320] lr: 2.0000e-03 eta: 1:47:26 time: 0.2525 data_time: 0.0105 memory: 13708 grad_norm: 5.0261 loss: 1.1346 top1_acc: 0.6364 top5_acc: 1.0000 loss_cls: 1.1346 2023/02/18 02:14:12 - mmengine - INFO - Epoch(val) [31][ 20/194] eta: 0:00:21 time: 0.1246 data_time: 0.0564 memory: 1818 2023/02/18 02:14:13 - mmengine - INFO - Epoch(val) [31][ 40/194] eta: 0:00:16 time: 0.0862 data_time: 0.0183 memory: 1818 2023/02/18 02:14:15 - mmengine - INFO - Epoch(val) [31][ 60/194] eta: 0:00:13 time: 0.0876 data_time: 0.0192 memory: 1818 2023/02/18 02:14:17 - mmengine - INFO - Epoch(val) [31][ 80/194] eta: 0:00:10 time: 0.0840 data_time: 0.0160 memory: 1818 2023/02/18 02:14:18 - mmengine - INFO - Epoch(val) [31][100/194] eta: 0:00:08 time: 0.0864 data_time: 0.0190 memory: 1818 2023/02/18 02:14:20 - mmengine - INFO - Epoch(val) [31][120/194] eta: 0:00:06 time: 0.0862 data_time: 0.0181 memory: 1818 2023/02/18 02:14:22 - mmengine - INFO - Epoch(val) [31][140/194] eta: 0:00:04 time: 0.0899 data_time: 0.0211 memory: 1818 2023/02/18 02:14:24 - mmengine - INFO - Epoch(val) [31][160/194] eta: 0:00:03 time: 0.0812 data_time: 0.0120 memory: 1818 2023/02/18 02:14:25 - mmengine - INFO - Epoch(val) [31][180/194] eta: 0:00:01 time: 0.0860 data_time: 0.0172 memory: 1818 2023/02/18 02:14:28 - mmengine - INFO - Epoch(val) [31][194/194] acc/top1: 0.5817 acc/top5: 0.8503 acc/mean1: 0.5148 2023/02/18 02:14:34 - mmengine - INFO - Epoch(train) [32][ 20/1320] lr: 2.0000e-03 eta: 1:47:22 time: 0.3064 data_time: 0.0455 memory: 13708 grad_norm: 5.0965 loss: 1.2730 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.2730 2023/02/18 02:14:39 - mmengine - INFO - Epoch(train) [32][ 40/1320] lr: 2.0000e-03 eta: 1:47:17 time: 0.2591 data_time: 0.0130 memory: 13708 grad_norm: 5.0908 loss: 1.2009 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.2009 2023/02/18 02:14:44 - mmengine - INFO - Epoch(train) [32][ 60/1320] lr: 2.0000e-03 eta: 1:47:12 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 5.0446 loss: 1.2633 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2633 2023/02/18 02:14:49 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:14:49 - mmengine - INFO - Epoch(train) [32][ 80/1320] lr: 2.0000e-03 eta: 1:47:06 time: 0.2557 data_time: 0.0101 memory: 13708 grad_norm: 5.1115 loss: 1.3006 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3006 2023/02/18 02:14:54 - mmengine - INFO - Epoch(train) [32][ 100/1320] lr: 2.0000e-03 eta: 1:47:01 time: 0.2547 data_time: 0.0102 memory: 13708 grad_norm: 5.0314 loss: 1.2764 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2764 2023/02/18 02:14:59 - mmengine - INFO - Epoch(train) [32][ 120/1320] lr: 2.0000e-03 eta: 1:46:56 time: 0.2569 data_time: 0.0123 memory: 13708 grad_norm: 4.9734 loss: 1.1072 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1072 2023/02/18 02:15:05 - mmengine - INFO - Epoch(train) [32][ 140/1320] lr: 2.0000e-03 eta: 1:46:51 time: 0.2559 data_time: 0.0106 memory: 13708 grad_norm: 5.0162 loss: 1.2597 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2597 2023/02/18 02:15:10 - mmengine - INFO - Epoch(train) [32][ 160/1320] lr: 2.0000e-03 eta: 1:46:46 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 4.9984 loss: 1.3221 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.3221 2023/02/18 02:15:15 - mmengine - INFO - Epoch(train) [32][ 180/1320] lr: 2.0000e-03 eta: 1:46:41 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 5.1751 loss: 1.3975 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3975 2023/02/18 02:15:20 - mmengine - INFO - Epoch(train) [32][ 200/1320] lr: 2.0000e-03 eta: 1:46:35 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 5.0988 loss: 1.1546 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1546 2023/02/18 02:15:25 - mmengine - INFO - Epoch(train) [32][ 220/1320] lr: 2.0000e-03 eta: 1:46:30 time: 0.2559 data_time: 0.0112 memory: 13708 grad_norm: 5.0709 loss: 1.2976 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.2976 2023/02/18 02:15:30 - mmengine - INFO - Epoch(train) [32][ 240/1320] lr: 2.0000e-03 eta: 1:46:25 time: 0.2553 data_time: 0.0104 memory: 13708 grad_norm: 5.1362 loss: 1.3250 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3250 2023/02/18 02:15:35 - mmengine - INFO - Epoch(train) [32][ 260/1320] lr: 2.0000e-03 eta: 1:46:20 time: 0.2549 data_time: 0.0108 memory: 13708 grad_norm: 5.1518 loss: 1.1662 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1662 2023/02/18 02:15:40 - mmengine - INFO - Epoch(train) [32][ 280/1320] lr: 2.0000e-03 eta: 1:46:15 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 5.0582 loss: 1.1267 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1267 2023/02/18 02:15:46 - mmengine - INFO - Epoch(train) [32][ 300/1320] lr: 2.0000e-03 eta: 1:46:10 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 5.1637 loss: 1.3622 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.3622 2023/02/18 02:15:51 - mmengine - INFO - Epoch(train) [32][ 320/1320] lr: 2.0000e-03 eta: 1:46:05 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 5.0242 loss: 1.4454 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4454 2023/02/18 02:15:56 - mmengine - INFO - Epoch(train) [32][ 340/1320] lr: 2.0000e-03 eta: 1:45:59 time: 0.2562 data_time: 0.0106 memory: 13708 grad_norm: 5.1044 loss: 1.3108 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.3108 2023/02/18 02:16:01 - mmengine - INFO - Epoch(train) [32][ 360/1320] lr: 2.0000e-03 eta: 1:45:54 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 5.0310 loss: 1.2518 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2518 2023/02/18 02:16:06 - mmengine - INFO - Epoch(train) [32][ 380/1320] lr: 2.0000e-03 eta: 1:45:49 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 5.1149 loss: 1.2873 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2873 2023/02/18 02:16:11 - mmengine - INFO - Epoch(train) [32][ 400/1320] lr: 2.0000e-03 eta: 1:45:44 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 5.1064 loss: 1.1287 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.1287 2023/02/18 02:16:16 - mmengine - INFO - Epoch(train) [32][ 420/1320] lr: 2.0000e-03 eta: 1:45:39 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 5.1031 loss: 1.0325 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0325 2023/02/18 02:16:21 - mmengine - INFO - Epoch(train) [32][ 440/1320] lr: 2.0000e-03 eta: 1:45:34 time: 0.2559 data_time: 0.0112 memory: 13708 grad_norm: 5.2111 loss: 1.2119 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.2119 2023/02/18 02:16:26 - mmengine - INFO - Epoch(train) [32][ 460/1320] lr: 2.0000e-03 eta: 1:45:28 time: 0.2549 data_time: 0.0103 memory: 13708 grad_norm: 5.0674 loss: 1.1382 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1382 2023/02/18 02:16:32 - mmengine - INFO - Epoch(train) [32][ 480/1320] lr: 2.0000e-03 eta: 1:45:23 time: 0.2556 data_time: 0.0112 memory: 13708 grad_norm: 5.0519 loss: 1.2491 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.2491 2023/02/18 02:16:37 - mmengine - INFO - Epoch(train) [32][ 500/1320] lr: 2.0000e-03 eta: 1:45:18 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 5.1187 loss: 1.2946 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2946 2023/02/18 02:16:42 - mmengine - INFO - Epoch(train) [32][ 520/1320] lr: 2.0000e-03 eta: 1:45:13 time: 0.2548 data_time: 0.0105 memory: 13708 grad_norm: 5.0909 loss: 1.2131 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.2131 2023/02/18 02:16:47 - mmengine - INFO - Epoch(train) [32][ 540/1320] lr: 2.0000e-03 eta: 1:45:08 time: 0.2552 data_time: 0.0104 memory: 13708 grad_norm: 4.9760 loss: 1.1152 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1152 2023/02/18 02:16:52 - mmengine - INFO - Epoch(train) [32][ 560/1320] lr: 2.0000e-03 eta: 1:45:03 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 5.3044 loss: 1.1216 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1216 2023/02/18 02:16:57 - mmengine - INFO - Epoch(train) [32][ 580/1320] lr: 2.0000e-03 eta: 1:44:57 time: 0.2561 data_time: 0.0114 memory: 13708 grad_norm: 5.2556 loss: 1.2344 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2344 2023/02/18 02:17:02 - mmengine - INFO - Epoch(train) [32][ 600/1320] lr: 2.0000e-03 eta: 1:44:52 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 5.1655 loss: 1.2142 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2142 2023/02/18 02:17:07 - mmengine - INFO - Epoch(train) [32][ 620/1320] lr: 2.0000e-03 eta: 1:44:47 time: 0.2564 data_time: 0.0107 memory: 13708 grad_norm: 5.1242 loss: 1.0990 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0990 2023/02/18 02:17:13 - mmengine - INFO - Epoch(train) [32][ 640/1320] lr: 2.0000e-03 eta: 1:44:42 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 5.1951 loss: 1.1079 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1079 2023/02/18 02:17:18 - mmengine - INFO - Epoch(train) [32][ 660/1320] lr: 2.0000e-03 eta: 1:44:37 time: 0.2563 data_time: 0.0112 memory: 13708 grad_norm: 5.1873 loss: 1.2890 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2890 2023/02/18 02:17:23 - mmengine - INFO - Epoch(train) [32][ 680/1320] lr: 2.0000e-03 eta: 1:44:32 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 5.1203 loss: 1.3410 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.3410 2023/02/18 02:17:28 - mmengine - INFO - Epoch(train) [32][ 700/1320] lr: 2.0000e-03 eta: 1:44:27 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 5.2641 loss: 1.2566 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2566 2023/02/18 02:17:33 - mmengine - INFO - Epoch(train) [32][ 720/1320] lr: 2.0000e-03 eta: 1:44:21 time: 0.2582 data_time: 0.0134 memory: 13708 grad_norm: 5.1827 loss: 1.1010 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.1010 2023/02/18 02:17:38 - mmengine - INFO - Epoch(train) [32][ 740/1320] lr: 2.0000e-03 eta: 1:44:16 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 5.1747 loss: 1.1412 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1412 2023/02/18 02:17:43 - mmengine - INFO - Epoch(train) [32][ 760/1320] lr: 2.0000e-03 eta: 1:44:11 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 5.0797 loss: 1.0773 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0773 2023/02/18 02:18:51 - mmengine - INFO - Epoch(train) [32][ 780/1320] lr: 2.0000e-03 eta: 1:44:43 time: 3.3952 data_time: 0.0109 memory: 13708 grad_norm: 5.2068 loss: 1.2741 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2741 2023/02/18 02:18:56 - mmengine - INFO - Epoch(train) [32][ 800/1320] lr: 2.0000e-03 eta: 1:44:37 time: 0.2563 data_time: 0.0104 memory: 13708 grad_norm: 5.2113 loss: 1.2331 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2331 2023/02/18 02:19:01 - mmengine - INFO - Epoch(train) [32][ 820/1320] lr: 2.0000e-03 eta: 1:44:32 time: 0.2567 data_time: 0.0111 memory: 13708 grad_norm: 5.1634 loss: 1.3076 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3076 2023/02/18 02:19:07 - mmengine - INFO - Epoch(train) [32][ 840/1320] lr: 2.0000e-03 eta: 1:44:27 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 5.1864 loss: 1.2301 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2301 2023/02/18 02:19:12 - mmengine - INFO - Epoch(train) [32][ 860/1320] lr: 2.0000e-03 eta: 1:44:22 time: 0.2558 data_time: 0.0111 memory: 13708 grad_norm: 5.1677 loss: 1.3486 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.3486 2023/02/18 02:19:17 - mmengine - INFO - Epoch(train) [32][ 880/1320] lr: 2.0000e-03 eta: 1:44:17 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 5.2386 loss: 1.2064 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2064 2023/02/18 02:19:22 - mmengine - INFO - Epoch(train) [32][ 900/1320] lr: 2.0000e-03 eta: 1:44:11 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 5.2111 loss: 1.1959 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1959 2023/02/18 02:19:27 - mmengine - INFO - Epoch(train) [32][ 920/1320] lr: 2.0000e-03 eta: 1:44:06 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 5.1915 loss: 1.3448 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3448 2023/02/18 02:19:32 - mmengine - INFO - Epoch(train) [32][ 940/1320] lr: 2.0000e-03 eta: 1:44:01 time: 0.2562 data_time: 0.0115 memory: 13708 grad_norm: 5.1623 loss: 1.0843 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0843 2023/02/18 02:19:37 - mmengine - INFO - Epoch(train) [32][ 960/1320] lr: 2.0000e-03 eta: 1:43:56 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 5.2379 loss: 1.2297 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2297 2023/02/18 02:19:42 - mmengine - INFO - Epoch(train) [32][ 980/1320] lr: 2.0000e-03 eta: 1:43:51 time: 0.2568 data_time: 0.0107 memory: 13708 grad_norm: 5.0911 loss: 1.1662 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1662 2023/02/18 02:19:48 - mmengine - INFO - Epoch(train) [32][1000/1320] lr: 2.0000e-03 eta: 1:43:45 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 5.1725 loss: 1.0805 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0805 2023/02/18 02:19:53 - mmengine - INFO - Epoch(train) [32][1020/1320] lr: 2.0000e-03 eta: 1:43:40 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 5.2503 loss: 1.1067 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1067 2023/02/18 02:19:58 - mmengine - INFO - Epoch(train) [32][1040/1320] lr: 2.0000e-03 eta: 1:43:35 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 5.1187 loss: 1.2222 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.2222 2023/02/18 02:20:03 - mmengine - INFO - Epoch(train) [32][1060/1320] lr: 2.0000e-03 eta: 1:43:30 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 5.3686 loss: 1.2255 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2255 2023/02/18 02:20:08 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:20:08 - mmengine - INFO - Epoch(train) [32][1080/1320] lr: 2.0000e-03 eta: 1:43:25 time: 0.2579 data_time: 0.0127 memory: 13708 grad_norm: 5.2432 loss: 1.3525 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.3525 2023/02/18 02:20:13 - mmengine - INFO - Epoch(train) [32][1100/1320] lr: 2.0000e-03 eta: 1:43:19 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 5.0719 loss: 1.2567 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2567 2023/02/18 02:20:18 - mmengine - INFO - Epoch(train) [32][1120/1320] lr: 2.0000e-03 eta: 1:43:14 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 5.1125 loss: 1.3164 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3164 2023/02/18 02:20:23 - mmengine - INFO - Epoch(train) [32][1140/1320] lr: 2.0000e-03 eta: 1:43:09 time: 0.2574 data_time: 0.0116 memory: 13708 grad_norm: 5.1069 loss: 1.3139 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3139 2023/02/18 02:20:29 - mmengine - INFO - Epoch(train) [32][1160/1320] lr: 2.0000e-03 eta: 1:43:04 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 5.3217 loss: 1.2567 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2567 2023/02/18 02:20:34 - mmengine - INFO - Epoch(train) [32][1180/1320] lr: 2.0000e-03 eta: 1:42:59 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 5.2771 loss: 1.3644 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.3644 2023/02/18 02:20:39 - mmengine - INFO - Epoch(train) [32][1200/1320] lr: 2.0000e-03 eta: 1:42:53 time: 0.2565 data_time: 0.0110 memory: 13708 grad_norm: 5.1405 loss: 1.4192 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.4192 2023/02/18 02:20:44 - mmengine - INFO - Epoch(train) [32][1220/1320] lr: 2.0000e-03 eta: 1:42:48 time: 0.2571 data_time: 0.0124 memory: 13708 grad_norm: 5.2561 loss: 1.3576 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3576 2023/02/18 02:20:49 - mmengine - INFO - Epoch(train) [32][1240/1320] lr: 2.0000e-03 eta: 1:42:43 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 5.1743 loss: 1.0934 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0934 2023/02/18 02:20:54 - mmengine - INFO - Epoch(train) [32][1260/1320] lr: 2.0000e-03 eta: 1:42:38 time: 0.2560 data_time: 0.0107 memory: 13708 grad_norm: 5.2399 loss: 1.2821 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.2821 2023/02/18 02:20:59 - mmengine - INFO - Epoch(train) [32][1280/1320] lr: 2.0000e-03 eta: 1:42:33 time: 0.2555 data_time: 0.0103 memory: 13708 grad_norm: 5.2187 loss: 1.4160 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.4160 2023/02/18 02:21:04 - mmengine - INFO - Epoch(train) [32][1300/1320] lr: 2.0000e-03 eta: 1:42:27 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 5.2182 loss: 1.3037 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.3037 2023/02/18 02:21:09 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:21:09 - mmengine - INFO - Epoch(train) [32][1320/1320] lr: 2.0000e-03 eta: 1:42:22 time: 0.2510 data_time: 0.0102 memory: 13708 grad_norm: 5.3957 loss: 1.2723 top1_acc: 0.8182 top5_acc: 0.9091 loss_cls: 1.2723 2023/02/18 02:21:12 - mmengine - INFO - Epoch(val) [32][ 20/194] eta: 0:00:22 time: 0.1306 data_time: 0.0632 memory: 1818 2023/02/18 02:21:14 - mmengine - INFO - Epoch(val) [32][ 40/194] eta: 0:00:16 time: 0.0865 data_time: 0.0188 memory: 1818 2023/02/18 02:21:16 - mmengine - INFO - Epoch(val) [32][ 60/194] eta: 0:00:13 time: 0.0890 data_time: 0.0209 memory: 1818 2023/02/18 02:21:17 - mmengine - INFO - Epoch(val) [32][ 80/194] eta: 0:00:11 time: 0.0879 data_time: 0.0191 memory: 1818 2023/02/18 02:21:19 - mmengine - INFO - Epoch(val) [32][100/194] eta: 0:00:08 time: 0.0847 data_time: 0.0165 memory: 1818 2023/02/18 02:21:21 - mmengine - INFO - Epoch(val) [32][120/194] eta: 0:00:06 time: 0.0856 data_time: 0.0172 memory: 1818 2023/02/18 02:21:22 - mmengine - INFO - Epoch(val) [32][140/194] eta: 0:00:05 time: 0.0843 data_time: 0.0155 memory: 1818 2023/02/18 02:21:24 - mmengine - INFO - Epoch(val) [32][160/194] eta: 0:00:03 time: 0.0823 data_time: 0.0136 memory: 1818 2023/02/18 02:21:26 - mmengine - INFO - Epoch(val) [32][180/194] eta: 0:00:01 time: 0.0894 data_time: 0.0210 memory: 1818 2023/02/18 02:21:28 - mmengine - INFO - Epoch(val) [32][194/194] acc/top1: 0.5871 acc/top5: 0.8516 acc/mean1: 0.5208 2023/02/18 02:21:34 - mmengine - INFO - Epoch(train) [33][ 20/1320] lr: 2.0000e-03 eta: 1:42:17 time: 0.3067 data_time: 0.0448 memory: 13708 grad_norm: 5.1593 loss: 1.0784 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0784 2023/02/18 02:21:39 - mmengine - INFO - Epoch(train) [33][ 40/1320] lr: 2.0000e-03 eta: 1:42:12 time: 0.2570 data_time: 0.0114 memory: 13708 grad_norm: 5.2632 loss: 1.0629 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0629 2023/02/18 02:21:44 - mmengine - INFO - Epoch(train) [33][ 60/1320] lr: 2.0000e-03 eta: 1:42:07 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 5.0700 loss: 1.0090 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0090 2023/02/18 02:21:50 - mmengine - INFO - Epoch(train) [33][ 80/1320] lr: 2.0000e-03 eta: 1:42:02 time: 0.2568 data_time: 0.0114 memory: 13708 grad_norm: 5.3016 loss: 1.2639 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2639 2023/02/18 02:21:55 - mmengine - INFO - Epoch(train) [33][ 100/1320] lr: 2.0000e-03 eta: 1:41:57 time: 0.2575 data_time: 0.0112 memory: 13708 grad_norm: 5.1389 loss: 1.1828 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1828 2023/02/18 02:22:00 - mmengine - INFO - Epoch(train) [33][ 120/1320] lr: 2.0000e-03 eta: 1:41:52 time: 0.2596 data_time: 0.0136 memory: 13708 grad_norm: 5.2431 loss: 1.2703 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2703 2023/02/18 02:22:05 - mmengine - INFO - Epoch(train) [33][ 140/1320] lr: 2.0000e-03 eta: 1:41:46 time: 0.2570 data_time: 0.0111 memory: 13708 grad_norm: 5.1522 loss: 1.1049 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1049 2023/02/18 02:22:10 - mmengine - INFO - Epoch(train) [33][ 160/1320] lr: 2.0000e-03 eta: 1:41:41 time: 0.2575 data_time: 0.0109 memory: 13708 grad_norm: 5.0744 loss: 1.1542 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1542 2023/02/18 02:22:15 - mmengine - INFO - Epoch(train) [33][ 180/1320] lr: 2.0000e-03 eta: 1:41:36 time: 0.2574 data_time: 0.0116 memory: 13708 grad_norm: 5.3869 loss: 1.1051 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1051 2023/02/18 02:22:21 - mmengine - INFO - Epoch(train) [33][ 200/1320] lr: 2.0000e-03 eta: 1:41:31 time: 0.2571 data_time: 0.0110 memory: 13708 grad_norm: 5.2387 loss: 1.4072 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.4072 2023/02/18 02:22:26 - mmengine - INFO - Epoch(train) [33][ 220/1320] lr: 2.0000e-03 eta: 1:41:26 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 5.2908 loss: 1.0386 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0386 2023/02/18 02:22:31 - mmengine - INFO - Epoch(train) [33][ 240/1320] lr: 2.0000e-03 eta: 1:41:20 time: 0.2556 data_time: 0.0103 memory: 13708 grad_norm: 5.1801 loss: 1.0612 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0612 2023/02/18 02:22:36 - mmengine - INFO - Epoch(train) [33][ 260/1320] lr: 2.0000e-03 eta: 1:41:15 time: 0.2549 data_time: 0.0098 memory: 13708 grad_norm: 5.3499 loss: 1.1285 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1285 2023/02/18 02:22:41 - mmengine - INFO - Epoch(train) [33][ 280/1320] lr: 2.0000e-03 eta: 1:41:10 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 5.2666 loss: 1.2910 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.2910 2023/02/18 02:22:46 - mmengine - INFO - Epoch(train) [33][ 300/1320] lr: 2.0000e-03 eta: 1:41:05 time: 0.2563 data_time: 0.0107 memory: 13708 grad_norm: 5.2749 loss: 1.1453 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1453 2023/02/18 02:22:51 - mmengine - INFO - Epoch(train) [33][ 320/1320] lr: 2.0000e-03 eta: 1:41:00 time: 0.2552 data_time: 0.0101 memory: 13708 grad_norm: 5.3717 loss: 1.3198 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.3198 2023/02/18 02:22:56 - mmengine - INFO - Epoch(train) [33][ 340/1320] lr: 2.0000e-03 eta: 1:40:54 time: 0.2554 data_time: 0.0103 memory: 13708 grad_norm: 5.2290 loss: 1.3895 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.3895 2023/02/18 02:23:01 - mmengine - INFO - Epoch(train) [33][ 360/1320] lr: 2.0000e-03 eta: 1:40:49 time: 0.2555 data_time: 0.0106 memory: 13708 grad_norm: 5.2283 loss: 1.2375 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.2375 2023/02/18 02:23:07 - mmengine - INFO - Epoch(train) [33][ 380/1320] lr: 2.0000e-03 eta: 1:40:44 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 5.2893 loss: 1.3856 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.3856 2023/02/18 02:23:12 - mmengine - INFO - Epoch(train) [33][ 400/1320] lr: 2.0000e-03 eta: 1:40:39 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 5.1411 loss: 1.0868 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0868 2023/02/18 02:23:17 - mmengine - INFO - Epoch(train) [33][ 420/1320] lr: 2.0000e-03 eta: 1:40:34 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 5.3128 loss: 1.1991 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1991 2023/02/18 02:23:22 - mmengine - INFO - Epoch(train) [33][ 440/1320] lr: 2.0000e-03 eta: 1:40:28 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 5.2056 loss: 1.2985 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.2985 2023/02/18 02:23:27 - mmengine - INFO - Epoch(train) [33][ 460/1320] lr: 2.0000e-03 eta: 1:40:23 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 5.3977 loss: 1.4211 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.4211 2023/02/18 02:23:32 - mmengine - INFO - Epoch(train) [33][ 480/1320] lr: 2.0000e-03 eta: 1:40:18 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 5.1735 loss: 1.1109 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1109 2023/02/18 02:23:37 - mmengine - INFO - Epoch(train) [33][ 500/1320] lr: 2.0000e-03 eta: 1:40:13 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 5.2854 loss: 1.2041 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.2041 2023/02/18 02:23:42 - mmengine - INFO - Epoch(train) [33][ 520/1320] lr: 2.0000e-03 eta: 1:40:08 time: 0.2558 data_time: 0.0111 memory: 13708 grad_norm: 5.2992 loss: 1.2891 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2891 2023/02/18 02:23:47 - mmengine - INFO - Epoch(train) [33][ 540/1320] lr: 2.0000e-03 eta: 1:40:02 time: 0.2557 data_time: 0.0103 memory: 13708 grad_norm: 5.2174 loss: 1.2415 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2415 2023/02/18 02:23:53 - mmengine - INFO - Epoch(train) [33][ 560/1320] lr: 2.0000e-03 eta: 1:39:57 time: 0.2569 data_time: 0.0114 memory: 13708 grad_norm: 5.3547 loss: 1.2553 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.2553 2023/02/18 02:23:58 - mmengine - INFO - Epoch(train) [33][ 580/1320] lr: 2.0000e-03 eta: 1:39:52 time: 0.2570 data_time: 0.0124 memory: 13708 grad_norm: 5.1140 loss: 1.1166 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1166 2023/02/18 02:24:03 - mmengine - INFO - Epoch(train) [33][ 600/1320] lr: 2.0000e-03 eta: 1:39:47 time: 0.2550 data_time: 0.0103 memory: 13708 grad_norm: 5.3046 loss: 1.1622 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.1622 2023/02/18 02:24:08 - mmengine - INFO - Epoch(train) [33][ 620/1320] lr: 2.0000e-03 eta: 1:39:42 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 5.3208 loss: 1.2133 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2133 2023/02/18 02:24:13 - mmengine - INFO - Epoch(train) [33][ 640/1320] lr: 2.0000e-03 eta: 1:39:36 time: 0.2558 data_time: 0.0103 memory: 13708 grad_norm: 5.2861 loss: 1.1390 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1390 2023/02/18 02:24:18 - mmengine - INFO - Epoch(train) [33][ 660/1320] lr: 2.0000e-03 eta: 1:39:31 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 5.2679 loss: 1.1444 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1444 2023/02/18 02:24:23 - mmengine - INFO - Epoch(train) [33][ 680/1320] lr: 2.0000e-03 eta: 1:39:26 time: 0.2576 data_time: 0.0121 memory: 13708 grad_norm: 5.2621 loss: 1.2065 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2065 2023/02/18 02:24:29 - mmengine - INFO - Epoch(train) [33][ 700/1320] lr: 2.0000e-03 eta: 1:39:21 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 5.2330 loss: 1.2642 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2642 2023/02/18 02:24:34 - mmengine - INFO - Epoch(train) [33][ 720/1320] lr: 2.0000e-03 eta: 1:39:16 time: 0.2553 data_time: 0.0107 memory: 13708 grad_norm: 5.3484 loss: 1.1457 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.1457 2023/02/18 02:24:39 - mmengine - INFO - Epoch(train) [33][ 740/1320] lr: 2.0000e-03 eta: 1:39:10 time: 0.2560 data_time: 0.0104 memory: 13708 grad_norm: 5.1934 loss: 1.1381 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.1381 2023/02/18 02:24:44 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:24:44 - mmengine - INFO - Epoch(train) [33][ 760/1320] lr: 2.0000e-03 eta: 1:39:05 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 5.4377 loss: 1.1865 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1865 2023/02/18 02:24:49 - mmengine - INFO - Epoch(train) [33][ 780/1320] lr: 2.0000e-03 eta: 1:39:00 time: 0.2568 data_time: 0.0112 memory: 13708 grad_norm: 5.3254 loss: 1.2332 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2332 2023/02/18 02:24:54 - mmengine - INFO - Epoch(train) [33][ 800/1320] lr: 2.0000e-03 eta: 1:38:55 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 5.3166 loss: 1.1408 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.1408 2023/02/18 02:24:59 - mmengine - INFO - Epoch(train) [33][ 820/1320] lr: 2.0000e-03 eta: 1:38:50 time: 0.2562 data_time: 0.0106 memory: 13708 grad_norm: 5.2460 loss: 1.0818 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0818 2023/02/18 02:25:04 - mmengine - INFO - Epoch(train) [33][ 840/1320] lr: 2.0000e-03 eta: 1:38:44 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 5.1773 loss: 1.1701 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1701 2023/02/18 02:25:09 - mmengine - INFO - Epoch(train) [33][ 860/1320] lr: 2.0000e-03 eta: 1:38:39 time: 0.2569 data_time: 0.0104 memory: 13708 grad_norm: 5.3148 loss: 1.2304 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2304 2023/02/18 02:25:15 - mmengine - INFO - Epoch(train) [33][ 880/1320] lr: 2.0000e-03 eta: 1:38:34 time: 0.2570 data_time: 0.0114 memory: 13708 grad_norm: 5.2399 loss: 1.2887 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2887 2023/02/18 02:25:20 - mmengine - INFO - Epoch(train) [33][ 900/1320] lr: 2.0000e-03 eta: 1:38:29 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 5.2517 loss: 1.0808 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0808 2023/02/18 02:25:25 - mmengine - INFO - Epoch(train) [33][ 920/1320] lr: 2.0000e-03 eta: 1:38:24 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 5.3839 loss: 1.2806 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2806 2023/02/18 02:25:30 - mmengine - INFO - Epoch(train) [33][ 940/1320] lr: 2.0000e-03 eta: 1:38:18 time: 0.2558 data_time: 0.0106 memory: 13708 grad_norm: 5.2450 loss: 1.1908 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.1908 2023/02/18 02:25:35 - mmengine - INFO - Epoch(train) [33][ 960/1320] lr: 2.0000e-03 eta: 1:38:13 time: 0.2555 data_time: 0.0111 memory: 13708 grad_norm: 5.4059 loss: 1.0861 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0861 2023/02/18 02:25:40 - mmengine - INFO - Epoch(train) [33][ 980/1320] lr: 2.0000e-03 eta: 1:38:08 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 5.4121 loss: 1.1526 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1526 2023/02/18 02:25:45 - mmengine - INFO - Epoch(train) [33][1000/1320] lr: 2.0000e-03 eta: 1:38:03 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 5.4936 loss: 1.2671 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2671 2023/02/18 02:25:50 - mmengine - INFO - Epoch(train) [33][1020/1320] lr: 2.0000e-03 eta: 1:37:58 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 5.3942 loss: 1.2556 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2556 2023/02/18 02:25:56 - mmengine - INFO - Epoch(train) [33][1040/1320] lr: 2.0000e-03 eta: 1:37:52 time: 0.2567 data_time: 0.0115 memory: 13708 grad_norm: 5.5320 loss: 1.3044 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.3044 2023/02/18 02:26:01 - mmengine - INFO - Epoch(train) [33][1060/1320] lr: 2.0000e-03 eta: 1:37:47 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 5.4246 loss: 1.2091 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2091 2023/02/18 02:26:06 - mmengine - INFO - Epoch(train) [33][1080/1320] lr: 2.0000e-03 eta: 1:37:42 time: 0.2562 data_time: 0.0105 memory: 13708 grad_norm: 5.4663 loss: 1.4763 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4763 2023/02/18 02:26:11 - mmengine - INFO - Epoch(train) [33][1100/1320] lr: 2.0000e-03 eta: 1:37:37 time: 0.2558 data_time: 0.0106 memory: 13708 grad_norm: 5.3161 loss: 1.3674 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3674 2023/02/18 02:26:16 - mmengine - INFO - Epoch(train) [33][1120/1320] lr: 2.0000e-03 eta: 1:37:32 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 5.4050 loss: 1.3680 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.3680 2023/02/18 02:26:21 - mmengine - INFO - Epoch(train) [33][1140/1320] lr: 2.0000e-03 eta: 1:37:26 time: 0.2581 data_time: 0.0124 memory: 13708 grad_norm: 5.4570 loss: 1.2471 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2471 2023/02/18 02:26:26 - mmengine - INFO - Epoch(train) [33][1160/1320] lr: 2.0000e-03 eta: 1:37:21 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 5.4046 loss: 1.1762 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1762 2023/02/18 02:26:31 - mmengine - INFO - Epoch(train) [33][1180/1320] lr: 2.0000e-03 eta: 1:37:16 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 5.2749 loss: 1.2524 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2524 2023/02/18 02:26:37 - mmengine - INFO - Epoch(train) [33][1200/1320] lr: 2.0000e-03 eta: 1:37:11 time: 0.2564 data_time: 0.0117 memory: 13708 grad_norm: 5.3663 loss: 1.3053 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.3053 2023/02/18 02:26:42 - mmengine - INFO - Epoch(train) [33][1220/1320] lr: 2.0000e-03 eta: 1:37:06 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 5.3919 loss: 1.4040 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.4040 2023/02/18 02:26:47 - mmengine - INFO - Epoch(train) [33][1240/1320] lr: 2.0000e-03 eta: 1:37:00 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 5.3557 loss: 1.1229 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1229 2023/02/18 02:26:52 - mmengine - INFO - Epoch(train) [33][1260/1320] lr: 2.0000e-03 eta: 1:36:55 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 5.3231 loss: 1.2924 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2924 2023/02/18 02:26:57 - mmengine - INFO - Epoch(train) [33][1280/1320] lr: 2.0000e-03 eta: 1:36:50 time: 0.2558 data_time: 0.0105 memory: 13708 grad_norm: 5.4021 loss: 1.0923 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.0923 2023/02/18 02:27:02 - mmengine - INFO - Epoch(train) [33][1300/1320] lr: 2.0000e-03 eta: 1:36:45 time: 0.2563 data_time: 0.0107 memory: 13708 grad_norm: 5.2320 loss: 1.2553 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2553 2023/02/18 02:27:07 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:27:07 - mmengine - INFO - Epoch(train) [33][1320/1320] lr: 2.0000e-03 eta: 1:36:40 time: 0.2514 data_time: 0.0104 memory: 13708 grad_norm: 5.5105 loss: 1.2738 top1_acc: 0.5455 top5_acc: 0.6364 loss_cls: 1.2738 2023/02/18 02:27:07 - mmengine - INFO - Saving checkpoint at 33 epochs 2023/02/18 02:27:11 - mmengine - INFO - Epoch(val) [33][ 20/194] eta: 0:00:22 time: 0.1300 data_time: 0.0596 memory: 1818 2023/02/18 02:27:13 - mmengine - INFO - Epoch(val) [33][ 40/194] eta: 0:00:17 time: 0.0928 data_time: 0.0246 memory: 1818 2023/02/18 02:27:15 - mmengine - INFO - Epoch(val) [33][ 60/194] eta: 0:00:13 time: 0.0858 data_time: 0.0175 memory: 1818 2023/02/18 02:27:16 - mmengine - INFO - Epoch(val) [33][ 80/194] eta: 0:00:11 time: 0.0856 data_time: 0.0178 memory: 1818 2023/02/18 02:27:18 - mmengine - INFO - Epoch(val) [33][100/194] eta: 0:00:09 time: 0.0934 data_time: 0.0243 memory: 1818 2023/02/18 02:27:20 - mmengine - INFO - Epoch(val) [33][120/194] eta: 0:00:07 time: 0.0874 data_time: 0.0172 memory: 1818 2023/02/18 02:27:22 - mmengine - INFO - Epoch(val) [33][140/194] eta: 0:00:05 time: 0.0883 data_time: 0.0204 memory: 1818 2023/02/18 02:27:23 - mmengine - INFO - Epoch(val) [33][160/194] eta: 0:00:03 time: 0.0884 data_time: 0.0200 memory: 1818 2023/02/18 02:27:25 - mmengine - INFO - Epoch(val) [33][180/194] eta: 0:00:01 time: 0.0799 data_time: 0.0148 memory: 1818 2023/02/18 02:27:27 - mmengine - INFO - Epoch(val) [33][194/194] acc/top1: 0.5853 acc/top5: 0.8505 acc/mean1: 0.5193 2023/02/18 02:27:33 - mmengine - INFO - Epoch(train) [34][ 20/1320] lr: 2.0000e-03 eta: 1:36:35 time: 0.3015 data_time: 0.0455 memory: 13708 grad_norm: 5.3853 loss: 1.2518 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2518 2023/02/18 02:27:38 - mmengine - INFO - Epoch(train) [34][ 40/1320] lr: 2.0000e-03 eta: 1:36:30 time: 0.2570 data_time: 0.0113 memory: 13708 grad_norm: 5.2829 loss: 1.0040 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0040 2023/02/18 02:27:43 - mmengine - INFO - Epoch(train) [34][ 60/1320] lr: 2.0000e-03 eta: 1:36:25 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 5.3074 loss: 1.1305 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1305 2023/02/18 02:27:48 - mmengine - INFO - Epoch(train) [34][ 80/1320] lr: 2.0000e-03 eta: 1:36:19 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 5.3371 loss: 1.1688 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1688 2023/02/18 02:27:53 - mmengine - INFO - Epoch(train) [34][ 100/1320] lr: 2.0000e-03 eta: 1:36:14 time: 0.2569 data_time: 0.0118 memory: 13708 grad_norm: 5.3450 loss: 1.1902 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1902 2023/02/18 02:27:59 - mmengine - INFO - Epoch(train) [34][ 120/1320] lr: 2.0000e-03 eta: 1:36:09 time: 0.2578 data_time: 0.0125 memory: 13708 grad_norm: 5.4373 loss: 1.2347 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2347 2023/02/18 02:28:04 - mmengine - INFO - Epoch(train) [34][ 140/1320] lr: 2.0000e-03 eta: 1:36:04 time: 0.2567 data_time: 0.0112 memory: 13708 grad_norm: 5.5483 loss: 1.3407 top1_acc: 0.3750 top5_acc: 0.9375 loss_cls: 1.3407 2023/02/18 02:28:09 - mmengine - INFO - Epoch(train) [34][ 160/1320] lr: 2.0000e-03 eta: 1:35:59 time: 0.2566 data_time: 0.0110 memory: 13708 grad_norm: 5.4223 loss: 1.2354 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2354 2023/02/18 02:28:14 - mmengine - INFO - Epoch(train) [34][ 180/1320] lr: 2.0000e-03 eta: 1:35:53 time: 0.2583 data_time: 0.0133 memory: 13708 grad_norm: 5.3907 loss: 1.1727 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1727 2023/02/18 02:28:19 - mmengine - INFO - Epoch(train) [34][ 200/1320] lr: 2.0000e-03 eta: 1:35:48 time: 0.2569 data_time: 0.0113 memory: 13708 grad_norm: 5.5493 loss: 1.1163 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1163 2023/02/18 02:28:24 - mmengine - INFO - Epoch(train) [34][ 220/1320] lr: 2.0000e-03 eta: 1:35:43 time: 0.2585 data_time: 0.0132 memory: 13708 grad_norm: 5.3702 loss: 1.1422 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1422 2023/02/18 02:28:29 - mmengine - INFO - Epoch(train) [34][ 240/1320] lr: 2.0000e-03 eta: 1:35:38 time: 0.2570 data_time: 0.0114 memory: 13708 grad_norm: 5.3338 loss: 1.1246 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1246 2023/02/18 02:28:35 - mmengine - INFO - Epoch(train) [34][ 260/1320] lr: 2.0000e-03 eta: 1:35:33 time: 0.2564 data_time: 0.0116 memory: 13708 grad_norm: 5.4843 loss: 1.3746 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.3746 2023/02/18 02:28:40 - mmengine - INFO - Epoch(train) [34][ 280/1320] lr: 2.0000e-03 eta: 1:35:28 time: 0.2567 data_time: 0.0114 memory: 13708 grad_norm: 5.3935 loss: 1.2259 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2259 2023/02/18 02:28:45 - mmengine - INFO - Epoch(train) [34][ 300/1320] lr: 2.0000e-03 eta: 1:35:22 time: 0.2563 data_time: 0.0115 memory: 13708 grad_norm: 5.5698 loss: 1.2067 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2067 2023/02/18 02:28:50 - mmengine - INFO - Epoch(train) [34][ 320/1320] lr: 2.0000e-03 eta: 1:35:17 time: 0.2562 data_time: 0.0114 memory: 13708 grad_norm: 5.4915 loss: 1.2244 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2244 2023/02/18 02:28:55 - mmengine - INFO - Epoch(train) [34][ 340/1320] lr: 2.0000e-03 eta: 1:35:12 time: 0.2568 data_time: 0.0117 memory: 13708 grad_norm: 5.4088 loss: 1.1081 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1081 2023/02/18 02:29:00 - mmengine - INFO - Epoch(train) [34][ 360/1320] lr: 2.0000e-03 eta: 1:35:07 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 5.3668 loss: 1.2481 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2481 2023/02/18 02:29:05 - mmengine - INFO - Epoch(train) [34][ 380/1320] lr: 2.0000e-03 eta: 1:35:02 time: 0.2569 data_time: 0.0113 memory: 13708 grad_norm: 5.3518 loss: 0.9986 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9986 2023/02/18 02:29:11 - mmengine - INFO - Epoch(train) [34][ 400/1320] lr: 2.0000e-03 eta: 1:34:56 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 5.5774 loss: 1.1585 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.1585 2023/02/18 02:29:16 - mmengine - INFO - Epoch(train) [34][ 420/1320] lr: 2.0000e-03 eta: 1:34:51 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 5.4969 loss: 1.2128 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2128 2023/02/18 02:29:21 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:29:21 - mmengine - INFO - Epoch(train) [34][ 440/1320] lr: 2.0000e-03 eta: 1:34:46 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 5.4899 loss: 1.1458 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1458 2023/02/18 02:29:26 - mmengine - INFO - Epoch(train) [34][ 460/1320] lr: 2.0000e-03 eta: 1:34:41 time: 0.2555 data_time: 0.0102 memory: 13708 grad_norm: 5.4529 loss: 1.1040 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1040 2023/02/18 02:29:31 - mmengine - INFO - Epoch(train) [34][ 480/1320] lr: 2.0000e-03 eta: 1:34:36 time: 0.2566 data_time: 0.0105 memory: 13708 grad_norm: 5.7016 loss: 1.0393 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0393 2023/02/18 02:29:36 - mmengine - INFO - Epoch(train) [34][ 500/1320] lr: 2.0000e-03 eta: 1:34:30 time: 0.2557 data_time: 0.0101 memory: 13708 grad_norm: 5.5156 loss: 1.2637 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.2637 2023/02/18 02:29:41 - mmengine - INFO - Epoch(train) [34][ 520/1320] lr: 2.0000e-03 eta: 1:34:25 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 5.4362 loss: 1.2523 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2523 2023/02/18 02:29:46 - mmengine - INFO - Epoch(train) [34][ 540/1320] lr: 2.0000e-03 eta: 1:34:20 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 5.4242 loss: 1.2940 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.2940 2023/02/18 02:29:51 - mmengine - INFO - Epoch(train) [34][ 560/1320] lr: 2.0000e-03 eta: 1:34:15 time: 0.2556 data_time: 0.0102 memory: 13708 grad_norm: 5.3572 loss: 1.2264 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.2264 2023/02/18 02:29:57 - mmengine - INFO - Epoch(train) [34][ 580/1320] lr: 2.0000e-03 eta: 1:34:10 time: 0.2553 data_time: 0.0110 memory: 13708 grad_norm: 5.5941 loss: 1.2232 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2232 2023/02/18 02:30:02 - mmengine - INFO - Epoch(train) [34][ 600/1320] lr: 2.0000e-03 eta: 1:34:04 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 5.4713 loss: 1.2132 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2132 2023/02/18 02:30:07 - mmengine - INFO - Epoch(train) [34][ 620/1320] lr: 2.0000e-03 eta: 1:33:59 time: 0.2555 data_time: 0.0110 memory: 13708 grad_norm: 5.4127 loss: 1.1384 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1384 2023/02/18 02:30:12 - mmengine - INFO - Epoch(train) [34][ 640/1320] lr: 2.0000e-03 eta: 1:33:54 time: 0.2560 data_time: 0.0112 memory: 13708 grad_norm: 5.3547 loss: 1.2130 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2130 2023/02/18 02:30:17 - mmengine - INFO - Epoch(train) [34][ 660/1320] lr: 2.0000e-03 eta: 1:33:49 time: 0.2559 data_time: 0.0105 memory: 13708 grad_norm: 5.4095 loss: 1.1111 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1111 2023/02/18 02:30:22 - mmengine - INFO - Epoch(train) [34][ 680/1320] lr: 2.0000e-03 eta: 1:33:44 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 5.3779 loss: 1.1565 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1565 2023/02/18 02:30:27 - mmengine - INFO - Epoch(train) [34][ 700/1320] lr: 2.0000e-03 eta: 1:33:38 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 5.5509 loss: 1.0593 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.0593 2023/02/18 02:30:32 - mmengine - INFO - Epoch(train) [34][ 720/1320] lr: 2.0000e-03 eta: 1:33:33 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 5.4753 loss: 1.1908 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1908 2023/02/18 02:30:38 - mmengine - INFO - Epoch(train) [34][ 740/1320] lr: 2.0000e-03 eta: 1:33:28 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 5.4681 loss: 1.3278 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3278 2023/02/18 02:30:43 - mmengine - INFO - Epoch(train) [34][ 760/1320] lr: 2.0000e-03 eta: 1:33:23 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 5.4287 loss: 1.1645 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1645 2023/02/18 02:30:48 - mmengine - INFO - Epoch(train) [34][ 780/1320] lr: 2.0000e-03 eta: 1:33:18 time: 0.2576 data_time: 0.0122 memory: 13708 grad_norm: 5.6045 loss: 1.2460 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2460 2023/02/18 02:30:53 - mmengine - INFO - Epoch(train) [34][ 800/1320] lr: 2.0000e-03 eta: 1:33:12 time: 0.2560 data_time: 0.0112 memory: 13708 grad_norm: 5.4818 loss: 1.2477 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2477 2023/02/18 02:30:58 - mmengine - INFO - Epoch(train) [34][ 820/1320] lr: 2.0000e-03 eta: 1:33:07 time: 0.2564 data_time: 0.0113 memory: 13708 grad_norm: 5.5909 loss: 1.2048 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2048 2023/02/18 02:31:03 - mmengine - INFO - Epoch(train) [34][ 840/1320] lr: 2.0000e-03 eta: 1:33:02 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 5.6653 loss: 1.2986 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.2986 2023/02/18 02:31:08 - mmengine - INFO - Epoch(train) [34][ 860/1320] lr: 2.0000e-03 eta: 1:32:57 time: 0.2566 data_time: 0.0107 memory: 13708 grad_norm: 5.3979 loss: 1.2489 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.2489 2023/02/18 02:31:13 - mmengine - INFO - Epoch(train) [34][ 880/1320] lr: 2.0000e-03 eta: 1:32:52 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 5.4764 loss: 1.3224 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3224 2023/02/18 02:31:19 - mmengine - INFO - Epoch(train) [34][ 900/1320] lr: 2.0000e-03 eta: 1:32:47 time: 0.2562 data_time: 0.0112 memory: 13708 grad_norm: 5.6308 loss: 1.1982 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1982 2023/02/18 02:31:24 - mmengine - INFO - Epoch(train) [34][ 920/1320] lr: 2.0000e-03 eta: 1:32:41 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 5.5801 loss: 1.2414 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2414 2023/02/18 02:31:29 - mmengine - INFO - Epoch(train) [34][ 940/1320] lr: 2.0000e-03 eta: 1:32:36 time: 0.2553 data_time: 0.0105 memory: 13708 grad_norm: 5.4435 loss: 1.0924 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0924 2023/02/18 02:31:34 - mmengine - INFO - Epoch(train) [34][ 960/1320] lr: 2.0000e-03 eta: 1:32:31 time: 0.2565 data_time: 0.0111 memory: 13708 grad_norm: 5.6117 loss: 1.2770 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.2770 2023/02/18 02:31:39 - mmengine - INFO - Epoch(train) [34][ 980/1320] lr: 2.0000e-03 eta: 1:32:26 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 5.5107 loss: 1.1141 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1141 2023/02/18 02:31:44 - mmengine - INFO - Epoch(train) [34][1000/1320] lr: 2.0000e-03 eta: 1:32:21 time: 0.2560 data_time: 0.0113 memory: 13708 grad_norm: 5.5280 loss: 1.1990 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.1990 2023/02/18 02:31:49 - mmengine - INFO - Epoch(train) [34][1020/1320] lr: 2.0000e-03 eta: 1:32:15 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 5.4309 loss: 1.2415 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2415 2023/02/18 02:31:54 - mmengine - INFO - Epoch(train) [34][1040/1320] lr: 2.0000e-03 eta: 1:32:10 time: 0.2564 data_time: 0.0104 memory: 13708 grad_norm: 5.4112 loss: 1.0836 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0836 2023/02/18 02:32:00 - mmengine - INFO - Epoch(train) [34][1060/1320] lr: 2.0000e-03 eta: 1:32:05 time: 0.2566 data_time: 0.0114 memory: 13708 grad_norm: 5.3392 loss: 1.0568 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0568 2023/02/18 02:32:05 - mmengine - INFO - Epoch(train) [34][1080/1320] lr: 2.0000e-03 eta: 1:32:00 time: 0.2557 data_time: 0.0104 memory: 13708 grad_norm: 5.6174 loss: 1.4828 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4828 2023/02/18 02:32:10 - mmengine - INFO - Epoch(train) [34][1100/1320] lr: 2.0000e-03 eta: 1:31:55 time: 0.2568 data_time: 0.0116 memory: 13708 grad_norm: 5.5482 loss: 1.0293 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0293 2023/02/18 02:32:15 - mmengine - INFO - Epoch(train) [34][1120/1320] lr: 2.0000e-03 eta: 1:31:49 time: 0.2564 data_time: 0.0106 memory: 13708 grad_norm: 5.3657 loss: 1.2065 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2065 2023/02/18 02:32:20 - mmengine - INFO - Epoch(train) [34][1140/1320] lr: 2.0000e-03 eta: 1:31:44 time: 0.2565 data_time: 0.0111 memory: 13708 grad_norm: 5.4264 loss: 1.2216 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2216 2023/02/18 02:32:25 - mmengine - INFO - Epoch(train) [34][1160/1320] lr: 2.0000e-03 eta: 1:31:39 time: 0.2563 data_time: 0.0112 memory: 13708 grad_norm: 5.6116 loss: 1.2792 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2792 2023/02/18 02:32:30 - mmengine - INFO - Epoch(train) [34][1180/1320] lr: 2.0000e-03 eta: 1:31:34 time: 0.2558 data_time: 0.0111 memory: 13708 grad_norm: 5.6541 loss: 1.2625 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2625 2023/02/18 02:32:35 - mmengine - INFO - Epoch(train) [34][1200/1320] lr: 2.0000e-03 eta: 1:31:29 time: 0.2562 data_time: 0.0110 memory: 13708 grad_norm: 5.3904 loss: 1.1553 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1553 2023/02/18 02:32:41 - mmengine - INFO - Epoch(train) [34][1220/1320] lr: 2.0000e-03 eta: 1:31:23 time: 0.2566 data_time: 0.0112 memory: 13708 grad_norm: 5.6858 loss: 1.3492 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3492 2023/02/18 02:32:46 - mmengine - INFO - Epoch(train) [34][1240/1320] lr: 2.0000e-03 eta: 1:31:18 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 5.4391 loss: 1.0829 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0829 2023/02/18 02:32:51 - mmengine - INFO - Epoch(train) [34][1260/1320] lr: 2.0000e-03 eta: 1:31:13 time: 0.2566 data_time: 0.0113 memory: 13708 grad_norm: 5.4900 loss: 1.2313 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2313 2023/02/18 02:32:56 - mmengine - INFO - Epoch(train) [34][1280/1320] lr: 2.0000e-03 eta: 1:31:08 time: 0.2563 data_time: 0.0116 memory: 13708 grad_norm: 5.5399 loss: 1.1813 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1813 2023/02/18 02:33:01 - mmengine - INFO - Epoch(train) [34][1300/1320] lr: 2.0000e-03 eta: 1:31:03 time: 0.2551 data_time: 0.0108 memory: 13708 grad_norm: 5.6086 loss: 1.1219 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1219 2023/02/18 02:33:06 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:33:06 - mmengine - INFO - Epoch(train) [34][1320/1320] lr: 2.0000e-03 eta: 1:30:57 time: 0.2514 data_time: 0.0101 memory: 13708 grad_norm: 5.7679 loss: 1.2997 top1_acc: 0.6364 top5_acc: 0.8182 loss_cls: 1.2997 2023/02/18 02:33:09 - mmengine - INFO - Epoch(val) [34][ 20/194] eta: 0:00:21 time: 0.1232 data_time: 0.0547 memory: 1818 2023/02/18 02:33:10 - mmengine - INFO - Epoch(val) [34][ 40/194] eta: 0:00:16 time: 0.0869 data_time: 0.0180 memory: 1818 2023/02/18 02:33:12 - mmengine - INFO - Epoch(val) [34][ 60/194] eta: 0:00:13 time: 0.0862 data_time: 0.0181 memory: 1818 2023/02/18 02:33:14 - mmengine - INFO - Epoch(val) [34][ 80/194] eta: 0:00:10 time: 0.0853 data_time: 0.0170 memory: 1818 2023/02/18 02:33:16 - mmengine - INFO - Epoch(val) [34][100/194] eta: 0:00:08 time: 0.0899 data_time: 0.0221 memory: 1818 2023/02/18 02:33:17 - mmengine - INFO - Epoch(val) [34][120/194] eta: 0:00:06 time: 0.0846 data_time: 0.0165 memory: 1818 2023/02/18 02:33:19 - mmengine - INFO - Epoch(val) [34][140/194] eta: 0:00:04 time: 0.0870 data_time: 0.0187 memory: 1818 2023/02/18 02:33:21 - mmengine - INFO - Epoch(val) [34][160/194] eta: 0:00:03 time: 0.0819 data_time: 0.0134 memory: 1818 2023/02/18 02:33:23 - mmengine - INFO - Epoch(val) [34][180/194] eta: 0:00:01 time: 0.0932 data_time: 0.0250 memory: 1818 2023/02/18 02:33:25 - mmengine - INFO - Epoch(val) [34][194/194] acc/top1: 0.5850 acc/top5: 0.8513 acc/mean1: 0.5225 2023/02/18 02:33:31 - mmengine - INFO - Epoch(train) [35][ 20/1320] lr: 2.0000e-03 eta: 1:30:53 time: 0.3030 data_time: 0.0427 memory: 13708 grad_norm: 5.6707 loss: 1.2377 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2377 2023/02/18 02:33:36 - mmengine - INFO - Epoch(train) [35][ 40/1320] lr: 2.0000e-03 eta: 1:30:48 time: 0.2560 data_time: 0.0101 memory: 13708 grad_norm: 5.4355 loss: 1.2225 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2225 2023/02/18 02:33:41 - mmengine - INFO - Epoch(train) [35][ 60/1320] lr: 2.0000e-03 eta: 1:30:42 time: 0.2549 data_time: 0.0104 memory: 13708 grad_norm: 5.4276 loss: 1.2562 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.2562 2023/02/18 02:33:46 - mmengine - INFO - Epoch(train) [35][ 80/1320] lr: 2.0000e-03 eta: 1:30:37 time: 0.2561 data_time: 0.0119 memory: 13708 grad_norm: 5.4829 loss: 1.1587 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1587 2023/02/18 02:33:51 - mmengine - INFO - Epoch(train) [35][ 100/1320] lr: 2.0000e-03 eta: 1:30:32 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 5.4843 loss: 1.0484 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0484 2023/02/18 02:33:56 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:33:56 - mmengine - INFO - Epoch(train) [35][ 120/1320] lr: 2.0000e-03 eta: 1:30:27 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 5.6531 loss: 1.2015 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2015 2023/02/18 02:34:01 - mmengine - INFO - Epoch(train) [35][ 140/1320] lr: 2.0000e-03 eta: 1:30:22 time: 0.2561 data_time: 0.0114 memory: 13708 grad_norm: 5.6155 loss: 1.0049 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0049 2023/02/18 02:34:06 - mmengine - INFO - Epoch(train) [35][ 160/1320] lr: 2.0000e-03 eta: 1:30:16 time: 0.2566 data_time: 0.0112 memory: 13708 grad_norm: 5.4771 loss: 1.2320 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2320 2023/02/18 02:34:12 - mmengine - INFO - Epoch(train) [35][ 180/1320] lr: 2.0000e-03 eta: 1:30:11 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 5.7622 loss: 1.1758 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1758 2023/02/18 02:34:17 - mmengine - INFO - Epoch(train) [35][ 200/1320] lr: 2.0000e-03 eta: 1:30:06 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 5.5828 loss: 1.1855 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1855 2023/02/18 02:34:22 - mmengine - INFO - Epoch(train) [35][ 220/1320] lr: 2.0000e-03 eta: 1:30:01 time: 0.2563 data_time: 0.0107 memory: 13708 grad_norm: 5.5418 loss: 1.1066 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1066 2023/02/18 02:34:27 - mmengine - INFO - Epoch(train) [35][ 240/1320] lr: 2.0000e-03 eta: 1:29:56 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 5.6191 loss: 1.1133 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1133 2023/02/18 02:34:32 - mmengine - INFO - Epoch(train) [35][ 260/1320] lr: 2.0000e-03 eta: 1:29:50 time: 0.2559 data_time: 0.0106 memory: 13708 grad_norm: 5.5385 loss: 1.1586 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1586 2023/02/18 02:34:37 - mmengine - INFO - Epoch(train) [35][ 280/1320] lr: 2.0000e-03 eta: 1:29:45 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 5.4003 loss: 1.2348 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2348 2023/02/18 02:34:42 - mmengine - INFO - Epoch(train) [35][ 300/1320] lr: 2.0000e-03 eta: 1:29:40 time: 0.2554 data_time: 0.0102 memory: 13708 grad_norm: 5.5670 loss: 1.1853 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1853 2023/02/18 02:34:47 - mmengine - INFO - Epoch(train) [35][ 320/1320] lr: 2.0000e-03 eta: 1:29:35 time: 0.2570 data_time: 0.0112 memory: 13708 grad_norm: 5.4717 loss: 1.0732 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.0732 2023/02/18 02:34:53 - mmengine - INFO - Epoch(train) [35][ 340/1320] lr: 2.0000e-03 eta: 1:29:30 time: 0.2560 data_time: 0.0107 memory: 13708 grad_norm: 5.5222 loss: 1.2519 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2519 2023/02/18 02:34:58 - mmengine - INFO - Epoch(train) [35][ 360/1320] lr: 2.0000e-03 eta: 1:29:24 time: 0.2564 data_time: 0.0106 memory: 13708 grad_norm: 5.4102 loss: 1.0416 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.0416 2023/02/18 02:35:03 - mmengine - INFO - Epoch(train) [35][ 380/1320] lr: 2.0000e-03 eta: 1:29:19 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 5.5551 loss: 1.2130 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.2130 2023/02/18 02:35:08 - mmengine - INFO - Epoch(train) [35][ 400/1320] lr: 2.0000e-03 eta: 1:29:14 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 5.6503 loss: 1.1014 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1014 2023/02/18 02:35:13 - mmengine - INFO - Epoch(train) [35][ 420/1320] lr: 2.0000e-03 eta: 1:29:09 time: 0.2561 data_time: 0.0113 memory: 13708 grad_norm: 5.5509 loss: 1.1519 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.1519 2023/02/18 02:35:18 - mmengine - INFO - Epoch(train) [35][ 440/1320] lr: 2.0000e-03 eta: 1:29:04 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 5.7445 loss: 1.2038 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2038 2023/02/18 02:35:23 - mmengine - INFO - Epoch(train) [35][ 460/1320] lr: 2.0000e-03 eta: 1:28:59 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 5.6575 loss: 1.1919 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1919 2023/02/18 02:35:28 - mmengine - INFO - Epoch(train) [35][ 480/1320] lr: 2.0000e-03 eta: 1:28:53 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 5.6194 loss: 1.2979 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2979 2023/02/18 02:35:34 - mmengine - INFO - Epoch(train) [35][ 500/1320] lr: 2.0000e-03 eta: 1:28:48 time: 0.2561 data_time: 0.0115 memory: 13708 grad_norm: 5.5538 loss: 1.2218 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2218 2023/02/18 02:35:39 - mmengine - INFO - Epoch(train) [35][ 520/1320] lr: 2.0000e-03 eta: 1:28:43 time: 0.2562 data_time: 0.0106 memory: 13708 grad_norm: 5.5915 loss: 1.2237 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2237 2023/02/18 02:35:44 - mmengine - INFO - Epoch(train) [35][ 540/1320] lr: 2.0000e-03 eta: 1:28:38 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 5.7172 loss: 1.2966 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2966 2023/02/18 02:35:49 - mmengine - INFO - Epoch(train) [35][ 560/1320] lr: 2.0000e-03 eta: 1:28:33 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 5.6050 loss: 1.0355 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0355 2023/02/18 02:35:54 - mmengine - INFO - Epoch(train) [35][ 580/1320] lr: 2.0000e-03 eta: 1:28:27 time: 0.2566 data_time: 0.0110 memory: 13708 grad_norm: 5.5943 loss: 1.2623 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2623 2023/02/18 02:35:59 - mmengine - INFO - Epoch(train) [35][ 600/1320] lr: 2.0000e-03 eta: 1:28:22 time: 0.2569 data_time: 0.0120 memory: 13708 grad_norm: 5.5193 loss: 1.1355 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1355 2023/02/18 02:36:04 - mmengine - INFO - Epoch(train) [35][ 620/1320] lr: 2.0000e-03 eta: 1:28:17 time: 0.2563 data_time: 0.0105 memory: 13708 grad_norm: 5.4843 loss: 1.1046 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1046 2023/02/18 02:36:09 - mmengine - INFO - Epoch(train) [35][ 640/1320] lr: 2.0000e-03 eta: 1:28:12 time: 0.2558 data_time: 0.0114 memory: 13708 grad_norm: 5.7114 loss: 1.2127 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2127 2023/02/18 02:36:15 - mmengine - INFO - Epoch(train) [35][ 660/1320] lr: 2.0000e-03 eta: 1:28:07 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 5.6352 loss: 1.2048 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2048 2023/02/18 02:36:20 - mmengine - INFO - Epoch(train) [35][ 680/1320] lr: 2.0000e-03 eta: 1:28:01 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 5.5946 loss: 1.0912 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0912 2023/02/18 02:36:25 - mmengine - INFO - Epoch(train) [35][ 700/1320] lr: 2.0000e-03 eta: 1:27:56 time: 0.2566 data_time: 0.0110 memory: 13708 grad_norm: 5.5049 loss: 1.1103 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1103 2023/02/18 02:36:30 - mmengine - INFO - Epoch(train) [35][ 720/1320] lr: 2.0000e-03 eta: 1:27:51 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 5.7341 loss: 1.1611 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1611 2023/02/18 02:36:35 - mmengine - INFO - Epoch(train) [35][ 740/1320] lr: 2.0000e-03 eta: 1:27:46 time: 0.2586 data_time: 0.0133 memory: 13708 grad_norm: 5.6071 loss: 1.1382 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1382 2023/02/18 02:36:40 - mmengine - INFO - Epoch(train) [35][ 760/1320] lr: 2.0000e-03 eta: 1:27:41 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 5.7992 loss: 1.0677 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0677 2023/02/18 02:36:45 - mmengine - INFO - Epoch(train) [35][ 780/1320] lr: 2.0000e-03 eta: 1:27:36 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 5.6604 loss: 1.0134 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0134 2023/02/18 02:36:50 - mmengine - INFO - Epoch(train) [35][ 800/1320] lr: 2.0000e-03 eta: 1:27:30 time: 0.2560 data_time: 0.0106 memory: 13708 grad_norm: 5.6266 loss: 1.2130 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2130 2023/02/18 02:36:56 - mmengine - INFO - Epoch(train) [35][ 820/1320] lr: 2.0000e-03 eta: 1:27:25 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 5.7805 loss: 1.0265 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0265 2023/02/18 02:37:01 - mmengine - INFO - Epoch(train) [35][ 840/1320] lr: 2.0000e-03 eta: 1:27:20 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 5.7397 loss: 1.1355 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1355 2023/02/18 02:37:06 - mmengine - INFO - Epoch(train) [35][ 860/1320] lr: 2.0000e-03 eta: 1:27:15 time: 0.2554 data_time: 0.0107 memory: 13708 grad_norm: 5.7644 loss: 1.1701 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1701 2023/02/18 02:37:11 - mmengine - INFO - Epoch(train) [35][ 880/1320] lr: 2.0000e-03 eta: 1:27:10 time: 0.2570 data_time: 0.0121 memory: 13708 grad_norm: 5.5978 loss: 1.0953 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0953 2023/02/18 02:37:16 - mmengine - INFO - Epoch(train) [35][ 900/1320] lr: 2.0000e-03 eta: 1:27:04 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 5.5649 loss: 1.0529 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0529 2023/02/18 02:37:21 - mmengine - INFO - Epoch(train) [35][ 920/1320] lr: 2.0000e-03 eta: 1:26:59 time: 0.2561 data_time: 0.0115 memory: 13708 grad_norm: 5.7303 loss: 1.2213 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2213 2023/02/18 02:37:26 - mmengine - INFO - Epoch(train) [35][ 940/1320] lr: 2.0000e-03 eta: 1:26:54 time: 0.2554 data_time: 0.0103 memory: 13708 grad_norm: 5.6434 loss: 1.0714 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0714 2023/02/18 02:37:31 - mmengine - INFO - Epoch(train) [35][ 960/1320] lr: 2.0000e-03 eta: 1:26:49 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 5.6470 loss: 1.0846 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0846 2023/02/18 02:37:37 - mmengine - INFO - Epoch(train) [35][ 980/1320] lr: 2.0000e-03 eta: 1:26:44 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 5.6790 loss: 1.2317 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2317 2023/02/18 02:37:42 - mmengine - INFO - Epoch(train) [35][1000/1320] lr: 2.0000e-03 eta: 1:26:38 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 5.7253 loss: 1.2050 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.2050 2023/02/18 02:37:47 - mmengine - INFO - Epoch(train) [35][1020/1320] lr: 2.0000e-03 eta: 1:26:33 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 5.7663 loss: 1.2463 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2463 2023/02/18 02:37:52 - mmengine - INFO - Epoch(train) [35][1040/1320] lr: 2.0000e-03 eta: 1:26:28 time: 0.2556 data_time: 0.0103 memory: 13708 grad_norm: 5.7453 loss: 1.1565 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1565 2023/02/18 02:37:57 - mmengine - INFO - Epoch(train) [35][1060/1320] lr: 2.0000e-03 eta: 1:26:23 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 5.8439 loss: 1.2084 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.2084 2023/02/18 02:38:02 - mmengine - INFO - Epoch(train) [35][1080/1320] lr: 2.0000e-03 eta: 1:26:18 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 5.8488 loss: 1.3157 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3157 2023/02/18 02:38:07 - mmengine - INFO - Epoch(train) [35][1100/1320] lr: 2.0000e-03 eta: 1:26:12 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 5.6989 loss: 1.1537 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1537 2023/02/18 02:38:12 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:38:12 - mmengine - INFO - Epoch(train) [35][1120/1320] lr: 2.0000e-03 eta: 1:26:07 time: 0.2561 data_time: 0.0115 memory: 13708 grad_norm: 5.6805 loss: 1.5113 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.5113 2023/02/18 02:38:18 - mmengine - INFO - Epoch(train) [35][1140/1320] lr: 2.0000e-03 eta: 1:26:02 time: 0.2561 data_time: 0.0105 memory: 13708 grad_norm: 5.6618 loss: 1.0702 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0702 2023/02/18 02:38:23 - mmengine - INFO - Epoch(train) [35][1160/1320] lr: 2.0000e-03 eta: 1:25:57 time: 0.2562 data_time: 0.0110 memory: 13708 grad_norm: 5.7999 loss: 1.3812 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3812 2023/02/18 02:38:28 - mmengine - INFO - Epoch(train) [35][1180/1320] lr: 2.0000e-03 eta: 1:25:52 time: 0.2583 data_time: 0.0121 memory: 13708 grad_norm: 5.6260 loss: 1.0561 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.0561 2023/02/18 02:38:33 - mmengine - INFO - Epoch(train) [35][1200/1320] lr: 2.0000e-03 eta: 1:25:47 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 5.7318 loss: 1.1202 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.1202 2023/02/18 02:38:38 - mmengine - INFO - Epoch(train) [35][1220/1320] lr: 2.0000e-03 eta: 1:25:41 time: 0.2563 data_time: 0.0112 memory: 13708 grad_norm: 5.8811 loss: 1.1832 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1832 2023/02/18 02:38:43 - mmengine - INFO - Epoch(train) [35][1240/1320] lr: 2.0000e-03 eta: 1:25:36 time: 0.2558 data_time: 0.0112 memory: 13708 grad_norm: 5.5373 loss: 1.1416 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1416 2023/02/18 02:38:48 - mmengine - INFO - Epoch(train) [35][1260/1320] lr: 2.0000e-03 eta: 1:25:31 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 5.7126 loss: 1.0748 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0748 2023/02/18 02:38:53 - mmengine - INFO - Epoch(train) [35][1280/1320] lr: 2.0000e-03 eta: 1:25:26 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 5.8438 loss: 1.2222 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2222 2023/02/18 02:38:59 - mmengine - INFO - Epoch(train) [35][1300/1320] lr: 2.0000e-03 eta: 1:25:21 time: 0.2560 data_time: 0.0106 memory: 13708 grad_norm: 5.7793 loss: 1.1393 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1393 2023/02/18 02:39:04 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:39:04 - mmengine - INFO - Epoch(train) [35][1320/1320] lr: 2.0000e-03 eta: 1:25:15 time: 0.2517 data_time: 0.0102 memory: 13708 grad_norm: 5.8543 loss: 1.2687 top1_acc: 0.3636 top5_acc: 0.8182 loss_cls: 1.2687 2023/02/18 02:39:06 - mmengine - INFO - Epoch(val) [35][ 20/194] eta: 0:00:21 time: 0.1240 data_time: 0.0553 memory: 1818 2023/02/18 02:39:08 - mmengine - INFO - Epoch(val) [35][ 40/194] eta: 0:00:16 time: 0.0876 data_time: 0.0194 memory: 1818 2023/02/18 02:39:10 - mmengine - INFO - Epoch(val) [35][ 60/194] eta: 0:00:13 time: 0.0886 data_time: 0.0203 memory: 1818 2023/02/18 02:39:11 - mmengine - INFO - Epoch(val) [35][ 80/194] eta: 0:00:10 time: 0.0856 data_time: 0.0177 memory: 1818 2023/02/18 02:39:13 - mmengine - INFO - Epoch(val) [35][100/194] eta: 0:00:08 time: 0.0923 data_time: 0.0240 memory: 1818 2023/02/18 02:39:15 - mmengine - INFO - Epoch(val) [35][120/194] eta: 0:00:06 time: 0.0841 data_time: 0.0160 memory: 1818 2023/02/18 02:39:17 - mmengine - INFO - Epoch(val) [35][140/194] eta: 0:00:05 time: 0.0877 data_time: 0.0189 memory: 1818 2023/02/18 02:39:18 - mmengine - INFO - Epoch(val) [35][160/194] eta: 0:00:03 time: 0.0816 data_time: 0.0132 memory: 1818 2023/02/18 02:39:20 - mmengine - INFO - Epoch(val) [35][180/194] eta: 0:00:01 time: 0.0841 data_time: 0.0157 memory: 1818 2023/02/18 02:39:22 - mmengine - INFO - Epoch(val) [35][194/194] acc/top1: 0.5877 acc/top5: 0.8519 acc/mean1: 0.5223 2023/02/18 02:39:22 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_30.pth is removed 2023/02/18 02:39:23 - mmengine - INFO - The best checkpoint with 0.5877 acc/top1 at 35 epoch is saved to best_acc/top1_epoch_35.pth. 2023/02/18 02:39:29 - mmengine - INFO - Epoch(train) [36][ 20/1320] lr: 2.0000e-03 eta: 1:25:11 time: 0.2937 data_time: 0.0417 memory: 13708 grad_norm: 5.6583 loss: 1.2019 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2019 2023/02/18 02:39:34 - mmengine - INFO - Epoch(train) [36][ 40/1320] lr: 2.0000e-03 eta: 1:25:05 time: 0.2569 data_time: 0.0106 memory: 13708 grad_norm: 5.7021 loss: 1.0449 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0449 2023/02/18 02:39:39 - mmengine - INFO - Epoch(train) [36][ 60/1320] lr: 2.0000e-03 eta: 1:25:00 time: 0.2565 data_time: 0.0107 memory: 13708 grad_norm: 5.5275 loss: 1.1317 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1317 2023/02/18 02:39:45 - mmengine - INFO - Epoch(train) [36][ 80/1320] lr: 2.0000e-03 eta: 1:24:55 time: 0.2554 data_time: 0.0103 memory: 13708 grad_norm: 5.6219 loss: 1.3054 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3054 2023/02/18 02:39:50 - mmengine - INFO - Epoch(train) [36][ 100/1320] lr: 2.0000e-03 eta: 1:24:50 time: 0.2569 data_time: 0.0125 memory: 13708 grad_norm: 5.7086 loss: 1.1951 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1951 2023/02/18 02:39:55 - mmengine - INFO - Epoch(train) [36][ 120/1320] lr: 2.0000e-03 eta: 1:24:45 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 5.7267 loss: 1.0544 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0544 2023/02/18 02:40:00 - mmengine - INFO - Epoch(train) [36][ 140/1320] lr: 2.0000e-03 eta: 1:24:39 time: 0.2557 data_time: 0.0104 memory: 13708 grad_norm: 5.6147 loss: 1.1994 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1994 2023/02/18 02:40:05 - mmengine - INFO - Epoch(train) [36][ 160/1320] lr: 2.0000e-03 eta: 1:24:34 time: 0.2576 data_time: 0.0120 memory: 13708 grad_norm: 5.7814 loss: 0.9768 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9768 2023/02/18 02:40:10 - mmengine - INFO - Epoch(train) [36][ 180/1320] lr: 2.0000e-03 eta: 1:24:29 time: 0.2560 data_time: 0.0107 memory: 13708 grad_norm: 5.7758 loss: 1.2134 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.2134 2023/02/18 02:40:15 - mmengine - INFO - Epoch(train) [36][ 200/1320] lr: 2.0000e-03 eta: 1:24:24 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 5.5882 loss: 1.1613 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1613 2023/02/18 02:40:20 - mmengine - INFO - Epoch(train) [36][ 220/1320] lr: 2.0000e-03 eta: 1:24:19 time: 0.2557 data_time: 0.0111 memory: 13708 grad_norm: 5.5852 loss: 1.3316 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3316 2023/02/18 02:40:26 - mmengine - INFO - Epoch(train) [36][ 240/1320] lr: 2.0000e-03 eta: 1:24:13 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 5.6025 loss: 1.1129 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1129 2023/02/18 02:40:31 - mmengine - INFO - Epoch(train) [36][ 260/1320] lr: 2.0000e-03 eta: 1:24:08 time: 0.2551 data_time: 0.0106 memory: 13708 grad_norm: 5.7919 loss: 1.2756 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2756 2023/02/18 02:40:36 - mmengine - INFO - Epoch(train) [36][ 280/1320] lr: 2.0000e-03 eta: 1:24:03 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 5.6013 loss: 1.0459 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0459 2023/02/18 02:40:41 - mmengine - INFO - Epoch(train) [36][ 300/1320] lr: 2.0000e-03 eta: 1:23:58 time: 0.2578 data_time: 0.0127 memory: 13708 grad_norm: 5.8317 loss: 1.1419 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1419 2023/02/18 02:40:46 - mmengine - INFO - Epoch(train) [36][ 320/1320] lr: 2.0000e-03 eta: 1:23:53 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 5.7922 loss: 1.0640 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0640 2023/02/18 02:40:51 - mmengine - INFO - Epoch(train) [36][ 340/1320] lr: 2.0000e-03 eta: 1:23:48 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 5.8004 loss: 1.1701 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.1701 2023/02/18 02:40:56 - mmengine - INFO - Epoch(train) [36][ 360/1320] lr: 2.0000e-03 eta: 1:23:42 time: 0.2564 data_time: 0.0108 memory: 13708 grad_norm: 5.6635 loss: 1.1715 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1715 2023/02/18 02:41:02 - mmengine - INFO - Epoch(train) [36][ 380/1320] lr: 2.0000e-03 eta: 1:23:37 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 5.5922 loss: 1.2137 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2137 2023/02/18 02:41:07 - mmengine - INFO - Epoch(train) [36][ 400/1320] lr: 2.0000e-03 eta: 1:23:32 time: 0.2562 data_time: 0.0110 memory: 13708 grad_norm: 5.7356 loss: 1.0981 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0981 2023/02/18 02:41:12 - mmengine - INFO - Epoch(train) [36][ 420/1320] lr: 2.0000e-03 eta: 1:23:27 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 5.9237 loss: 1.2454 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2454 2023/02/18 02:41:17 - mmengine - INFO - Epoch(train) [36][ 440/1320] lr: 2.0000e-03 eta: 1:23:22 time: 0.2566 data_time: 0.0117 memory: 13708 grad_norm: 5.7973 loss: 1.2129 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2129 2023/02/18 02:41:22 - mmengine - INFO - Epoch(train) [36][ 460/1320] lr: 2.0000e-03 eta: 1:23:16 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 5.8124 loss: 1.2001 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2001 2023/02/18 02:41:27 - mmengine - INFO - Epoch(train) [36][ 480/1320] lr: 2.0000e-03 eta: 1:23:11 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 5.6002 loss: 1.2083 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2083 2023/02/18 02:41:32 - mmengine - INFO - Epoch(train) [36][ 500/1320] lr: 2.0000e-03 eta: 1:23:06 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 5.7997 loss: 0.9809 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9809 2023/02/18 02:41:37 - mmengine - INFO - Epoch(train) [36][ 520/1320] lr: 2.0000e-03 eta: 1:23:01 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 5.5744 loss: 1.1222 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1222 2023/02/18 02:41:43 - mmengine - INFO - Epoch(train) [36][ 540/1320] lr: 2.0000e-03 eta: 1:22:56 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 5.6798 loss: 1.0249 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0249 2023/02/18 02:41:48 - mmengine - INFO - Epoch(train) [36][ 560/1320] lr: 2.0000e-03 eta: 1:22:50 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 5.7020 loss: 1.1827 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1827 2023/02/18 02:41:53 - mmengine - INFO - Epoch(train) [36][ 580/1320] lr: 2.0000e-03 eta: 1:22:45 time: 0.2553 data_time: 0.0103 memory: 13708 grad_norm: 5.7340 loss: 1.0980 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0980 2023/02/18 02:41:58 - mmengine - INFO - Epoch(train) [36][ 600/1320] lr: 2.0000e-03 eta: 1:22:40 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 5.7555 loss: 1.1555 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1555 2023/02/18 02:42:03 - mmengine - INFO - Epoch(train) [36][ 620/1320] lr: 2.0000e-03 eta: 1:22:35 time: 0.2565 data_time: 0.0106 memory: 13708 grad_norm: 5.8864 loss: 1.0950 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.0950 2023/02/18 02:42:08 - mmengine - INFO - Epoch(train) [36][ 640/1320] lr: 2.0000e-03 eta: 1:22:30 time: 0.2563 data_time: 0.0117 memory: 13708 grad_norm: 5.9309 loss: 1.2506 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2506 2023/02/18 02:42:13 - mmengine - INFO - Epoch(train) [36][ 660/1320] lr: 2.0000e-03 eta: 1:22:25 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 5.8623 loss: 1.2058 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2058 2023/02/18 02:42:18 - mmengine - INFO - Epoch(train) [36][ 680/1320] lr: 2.0000e-03 eta: 1:22:19 time: 0.2573 data_time: 0.0120 memory: 13708 grad_norm: 5.9861 loss: 1.2840 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.2840 2023/02/18 02:42:24 - mmengine - INFO - Epoch(train) [36][ 700/1320] lr: 2.0000e-03 eta: 1:22:14 time: 0.2567 data_time: 0.0113 memory: 13708 grad_norm: 5.8066 loss: 1.1160 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1160 2023/02/18 02:42:29 - mmengine - INFO - Epoch(train) [36][ 720/1320] lr: 2.0000e-03 eta: 1:22:09 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 5.6708 loss: 1.0769 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0769 2023/02/18 02:42:34 - mmengine - INFO - Epoch(train) [36][ 740/1320] lr: 2.0000e-03 eta: 1:22:04 time: 0.2554 data_time: 0.0103 memory: 13708 grad_norm: 5.8380 loss: 1.0907 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0907 2023/02/18 02:42:39 - mmengine - INFO - Epoch(train) [36][ 760/1320] lr: 2.0000e-03 eta: 1:21:59 time: 0.2559 data_time: 0.0112 memory: 13708 grad_norm: 5.6385 loss: 1.1451 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1451 2023/02/18 02:42:44 - mmengine - INFO - Epoch(train) [36][ 780/1320] lr: 2.0000e-03 eta: 1:21:53 time: 0.2568 data_time: 0.0109 memory: 13708 grad_norm: 5.7782 loss: 1.2706 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2706 2023/02/18 02:42:49 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:42:49 - mmengine - INFO - Epoch(train) [36][ 800/1320] lr: 2.0000e-03 eta: 1:21:48 time: 0.2560 data_time: 0.0106 memory: 13708 grad_norm: 5.8053 loss: 1.1273 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1273 2023/02/18 02:42:54 - mmengine - INFO - Epoch(train) [36][ 820/1320] lr: 2.0000e-03 eta: 1:21:43 time: 0.2560 data_time: 0.0107 memory: 13708 grad_norm: 5.7128 loss: 1.1658 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1658 2023/02/18 02:42:59 - mmengine - INFO - Epoch(train) [36][ 840/1320] lr: 2.0000e-03 eta: 1:21:38 time: 0.2580 data_time: 0.0132 memory: 13708 grad_norm: 5.7954 loss: 1.2595 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2595 2023/02/18 02:43:05 - mmengine - INFO - Epoch(train) [36][ 860/1320] lr: 2.0000e-03 eta: 1:21:33 time: 0.2560 data_time: 0.0113 memory: 13708 grad_norm: 5.9334 loss: 1.3294 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3294 2023/02/18 02:43:10 - mmengine - INFO - Epoch(train) [36][ 880/1320] lr: 2.0000e-03 eta: 1:21:28 time: 0.2581 data_time: 0.0136 memory: 13708 grad_norm: 5.9613 loss: 1.2130 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2130 2023/02/18 02:43:15 - mmengine - INFO - Epoch(train) [36][ 900/1320] lr: 2.0000e-03 eta: 1:21:22 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 5.9800 loss: 1.3346 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.3346 2023/02/18 02:43:20 - mmengine - INFO - Epoch(train) [36][ 920/1320] lr: 2.0000e-03 eta: 1:21:17 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 5.9202 loss: 1.3088 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3088 2023/02/18 02:43:25 - mmengine - INFO - Epoch(train) [36][ 940/1320] lr: 2.0000e-03 eta: 1:21:12 time: 0.2587 data_time: 0.0128 memory: 13708 grad_norm: 5.8219 loss: 1.1498 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.1498 2023/02/18 02:43:30 - mmengine - INFO - Epoch(train) [36][ 960/1320] lr: 2.0000e-03 eta: 1:21:07 time: 0.2558 data_time: 0.0104 memory: 13708 grad_norm: 6.0181 loss: 1.2738 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2738 2023/02/18 02:43:35 - mmengine - INFO - Epoch(train) [36][ 980/1320] lr: 2.0000e-03 eta: 1:21:02 time: 0.2562 data_time: 0.0115 memory: 13708 grad_norm: 5.8904 loss: 1.1887 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.1887 2023/02/18 02:43:41 - mmengine - INFO - Epoch(train) [36][1000/1320] lr: 2.0000e-03 eta: 1:20:56 time: 0.2560 data_time: 0.0104 memory: 13708 grad_norm: 5.8223 loss: 1.1719 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1719 2023/02/18 02:43:46 - mmengine - INFO - Epoch(train) [36][1020/1320] lr: 2.0000e-03 eta: 1:20:51 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 5.8901 loss: 1.1084 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.1084 2023/02/18 02:43:51 - mmengine - INFO - Epoch(train) [36][1040/1320] lr: 2.0000e-03 eta: 1:20:46 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 5.9700 loss: 1.0839 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0839 2023/02/18 02:43:56 - mmengine - INFO - Epoch(train) [36][1060/1320] lr: 2.0000e-03 eta: 1:20:41 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 5.9171 loss: 1.1897 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1897 2023/02/18 02:44:01 - mmengine - INFO - Epoch(train) [36][1080/1320] lr: 2.0000e-03 eta: 1:20:36 time: 0.2560 data_time: 0.0111 memory: 13708 grad_norm: 5.8764 loss: 1.0964 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0964 2023/02/18 02:44:06 - mmengine - INFO - Epoch(train) [36][1100/1320] lr: 2.0000e-03 eta: 1:20:31 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 5.8430 loss: 1.1711 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1711 2023/02/18 02:44:11 - mmengine - INFO - Epoch(train) [36][1120/1320] lr: 2.0000e-03 eta: 1:20:25 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 5.9212 loss: 1.1389 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1389 2023/02/18 02:44:16 - mmengine - INFO - Epoch(train) [36][1140/1320] lr: 2.0000e-03 eta: 1:20:20 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 5.8840 loss: 1.1664 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1664 2023/02/18 02:44:22 - mmengine - INFO - Epoch(train) [36][1160/1320] lr: 2.0000e-03 eta: 1:20:15 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 5.9063 loss: 1.1353 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1353 2023/02/18 02:44:27 - mmengine - INFO - Epoch(train) [36][1180/1320] lr: 2.0000e-03 eta: 1:20:10 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 5.7236 loss: 0.9899 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9899 2023/02/18 02:44:32 - mmengine - INFO - Epoch(train) [36][1200/1320] lr: 2.0000e-03 eta: 1:20:05 time: 0.2567 data_time: 0.0117 memory: 13708 grad_norm: 5.6767 loss: 1.1150 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1150 2023/02/18 02:44:37 - mmengine - INFO - Epoch(train) [36][1220/1320] lr: 2.0000e-03 eta: 1:19:59 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 5.8792 loss: 1.1096 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1096 2023/02/18 02:44:42 - mmengine - INFO - Epoch(train) [36][1240/1320] lr: 2.0000e-03 eta: 1:19:54 time: 0.2558 data_time: 0.0112 memory: 13708 grad_norm: 5.9054 loss: 1.1821 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1821 2023/02/18 02:44:47 - mmengine - INFO - Epoch(train) [36][1260/1320] lr: 2.0000e-03 eta: 1:19:49 time: 0.2566 data_time: 0.0110 memory: 13708 grad_norm: 5.8041 loss: 1.3931 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3931 2023/02/18 02:44:52 - mmengine - INFO - Epoch(train) [36][1280/1320] lr: 2.0000e-03 eta: 1:19:44 time: 0.2569 data_time: 0.0107 memory: 13708 grad_norm: 5.7655 loss: 1.0394 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0394 2023/02/18 02:44:57 - mmengine - INFO - Epoch(train) [36][1300/1320] lr: 2.0000e-03 eta: 1:19:39 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 5.8639 loss: 1.2113 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.2113 2023/02/18 02:45:02 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:45:02 - mmengine - INFO - Epoch(train) [36][1320/1320] lr: 2.0000e-03 eta: 1:19:33 time: 0.2535 data_time: 0.0127 memory: 13708 grad_norm: 5.9805 loss: 1.1031 top1_acc: 0.5455 top5_acc: 0.8182 loss_cls: 1.1031 2023/02/18 02:45:02 - mmengine - INFO - Saving checkpoint at 36 epochs 2023/02/18 02:45:06 - mmengine - INFO - Epoch(val) [36][ 20/194] eta: 0:00:22 time: 0.1283 data_time: 0.0588 memory: 1818 2023/02/18 02:45:08 - mmengine - INFO - Epoch(val) [36][ 40/194] eta: 0:00:16 time: 0.0884 data_time: 0.0178 memory: 1818 2023/02/18 02:45:10 - mmengine - INFO - Epoch(val) [36][ 60/194] eta: 0:00:13 time: 0.0862 data_time: 0.0176 memory: 1818 2023/02/18 02:45:11 - mmengine - INFO - Epoch(val) [36][ 80/194] eta: 0:00:11 time: 0.0833 data_time: 0.0144 memory: 1818 2023/02/18 02:45:13 - mmengine - INFO - Epoch(val) [36][100/194] eta: 0:00:08 time: 0.0865 data_time: 0.0179 memory: 1818 2023/02/18 02:45:15 - mmengine - INFO - Epoch(val) [36][120/194] eta: 0:00:06 time: 0.0867 data_time: 0.0178 memory: 1818 2023/02/18 02:45:17 - mmengine - INFO - Epoch(val) [36][140/194] eta: 0:00:04 time: 0.0865 data_time: 0.0177 memory: 1818 2023/02/18 02:45:18 - mmengine - INFO - Epoch(val) [36][160/194] eta: 0:00:03 time: 0.0824 data_time: 0.0128 memory: 1818 2023/02/18 02:45:20 - mmengine - INFO - Epoch(val) [36][180/194] eta: 0:00:01 time: 0.0822 data_time: 0.0147 memory: 1818 2023/02/18 02:45:22 - mmengine - INFO - Epoch(val) [36][194/194] acc/top1: 0.5879 acc/top5: 0.8506 acc/mean1: 0.5221 2023/02/18 02:45:22 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_35.pth is removed 2023/02/18 02:45:22 - mmengine - INFO - The best checkpoint with 0.5879 acc/top1 at 36 epoch is saved to best_acc/top1_epoch_36.pth. 2023/02/18 02:45:28 - mmengine - INFO - Epoch(train) [37][ 20/1320] lr: 2.0000e-03 eta: 1:19:29 time: 0.2910 data_time: 0.0381 memory: 13708 grad_norm: 5.7374 loss: 1.0958 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0958 2023/02/18 02:45:33 - mmengine - INFO - Epoch(train) [37][ 40/1320] lr: 2.0000e-03 eta: 1:19:23 time: 0.2569 data_time: 0.0113 memory: 13708 grad_norm: 5.7258 loss: 1.0675 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.0675 2023/02/18 02:45:39 - mmengine - INFO - Epoch(train) [37][ 60/1320] lr: 2.0000e-03 eta: 1:19:18 time: 0.2560 data_time: 0.0105 memory: 13708 grad_norm: 5.8242 loss: 1.1685 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1685 2023/02/18 02:45:44 - mmengine - INFO - Epoch(train) [37][ 80/1320] lr: 2.0000e-03 eta: 1:19:13 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 5.8888 loss: 1.1975 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1975 2023/02/18 02:45:49 - mmengine - INFO - Epoch(train) [37][ 100/1320] lr: 2.0000e-03 eta: 1:19:08 time: 0.2558 data_time: 0.0106 memory: 13708 grad_norm: 5.9496 loss: 1.1905 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1905 2023/02/18 02:45:54 - mmengine - INFO - Epoch(train) [37][ 120/1320] lr: 2.0000e-03 eta: 1:19:03 time: 0.2566 data_time: 0.0112 memory: 13708 grad_norm: 5.9052 loss: 1.1658 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1658 2023/02/18 02:45:59 - mmengine - INFO - Epoch(train) [37][ 140/1320] lr: 2.0000e-03 eta: 1:18:57 time: 0.2565 data_time: 0.0114 memory: 13708 grad_norm: 5.8912 loss: 1.2412 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2412 2023/02/18 02:46:04 - mmengine - INFO - Epoch(train) [37][ 160/1320] lr: 2.0000e-03 eta: 1:18:52 time: 0.2550 data_time: 0.0105 memory: 13708 grad_norm: 5.9747 loss: 1.1459 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1459 2023/02/18 02:46:09 - mmengine - INFO - Epoch(train) [37][ 180/1320] lr: 2.0000e-03 eta: 1:18:47 time: 0.2564 data_time: 0.0113 memory: 13708 grad_norm: 5.8171 loss: 1.1192 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1192 2023/02/18 02:46:14 - mmengine - INFO - Epoch(train) [37][ 200/1320] lr: 2.0000e-03 eta: 1:18:42 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 5.7442 loss: 1.1142 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1142 2023/02/18 02:46:19 - mmengine - INFO - Epoch(train) [37][ 220/1320] lr: 2.0000e-03 eta: 1:18:37 time: 0.2548 data_time: 0.0102 memory: 13708 grad_norm: 5.7090 loss: 1.0603 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0603 2023/02/18 02:46:25 - mmengine - INFO - Epoch(train) [37][ 240/1320] lr: 2.0000e-03 eta: 1:18:32 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 6.0595 loss: 1.3163 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3163 2023/02/18 02:46:30 - mmengine - INFO - Epoch(train) [37][ 260/1320] lr: 2.0000e-03 eta: 1:18:26 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 5.8204 loss: 1.1154 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1154 2023/02/18 02:46:35 - mmengine - INFO - Epoch(train) [37][ 280/1320] lr: 2.0000e-03 eta: 1:18:21 time: 0.2566 data_time: 0.0112 memory: 13708 grad_norm: 5.8659 loss: 1.2707 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.2707 2023/02/18 02:46:40 - mmengine - INFO - Epoch(train) [37][ 300/1320] lr: 2.0000e-03 eta: 1:18:16 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 6.0705 loss: 1.2868 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2868 2023/02/18 02:46:45 - mmengine - INFO - Epoch(train) [37][ 320/1320] lr: 2.0000e-03 eta: 1:18:11 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 5.9998 loss: 1.0926 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0926 2023/02/18 02:46:50 - mmengine - INFO - Epoch(train) [37][ 340/1320] lr: 2.0000e-03 eta: 1:18:06 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 6.0130 loss: 1.2108 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 1.2108 2023/02/18 02:46:55 - mmengine - INFO - Epoch(train) [37][ 360/1320] lr: 2.0000e-03 eta: 1:18:00 time: 0.2566 data_time: 0.0107 memory: 13708 grad_norm: 5.7637 loss: 1.1759 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1759 2023/02/18 02:47:00 - mmengine - INFO - Epoch(train) [37][ 380/1320] lr: 2.0000e-03 eta: 1:17:55 time: 0.2554 data_time: 0.0103 memory: 13708 grad_norm: 6.0654 loss: 1.2379 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.2379 2023/02/18 02:47:06 - mmengine - INFO - Epoch(train) [37][ 400/1320] lr: 2.0000e-03 eta: 1:17:50 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 5.8514 loss: 1.1618 top1_acc: 0.4375 top5_acc: 1.0000 loss_cls: 1.1618 2023/02/18 02:47:11 - mmengine - INFO - Epoch(train) [37][ 420/1320] lr: 2.0000e-03 eta: 1:17:45 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 5.8669 loss: 1.0308 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0308 2023/02/18 02:47:16 - mmengine - INFO - Epoch(train) [37][ 440/1320] lr: 2.0000e-03 eta: 1:17:40 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 5.9379 loss: 1.1199 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.1199 2023/02/18 02:47:21 - mmengine - INFO - Epoch(train) [37][ 460/1320] lr: 2.0000e-03 eta: 1:17:35 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 6.0824 loss: 1.2824 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2824 2023/02/18 02:47:26 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:47:26 - mmengine - INFO - Epoch(train) [37][ 480/1320] lr: 2.0000e-03 eta: 1:17:29 time: 0.2562 data_time: 0.0113 memory: 13708 grad_norm: 5.8055 loss: 1.0813 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0813 2023/02/18 02:47:31 - mmengine - INFO - Epoch(train) [37][ 500/1320] lr: 2.0000e-03 eta: 1:17:24 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 5.9551 loss: 1.1812 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.1812 2023/02/18 02:47:36 - mmengine - INFO - Epoch(train) [37][ 520/1320] lr: 2.0000e-03 eta: 1:17:19 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 5.8807 loss: 1.1920 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1920 2023/02/18 02:47:41 - mmengine - INFO - Epoch(train) [37][ 540/1320] lr: 2.0000e-03 eta: 1:17:14 time: 0.2555 data_time: 0.0105 memory: 13708 grad_norm: 5.9454 loss: 1.1075 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.1075 2023/02/18 02:47:47 - mmengine - INFO - Epoch(train) [37][ 560/1320] lr: 2.0000e-03 eta: 1:17:09 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 5.9746 loss: 1.1932 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1932 2023/02/18 02:47:52 - mmengine - INFO - Epoch(train) [37][ 580/1320] lr: 2.0000e-03 eta: 1:17:03 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 5.9655 loss: 1.2215 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.2215 2023/02/18 02:47:57 - mmengine - INFO - Epoch(train) [37][ 600/1320] lr: 2.0000e-03 eta: 1:16:58 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 6.3516 loss: 1.1751 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1751 2023/02/18 02:48:02 - mmengine - INFO - Epoch(train) [37][ 620/1320] lr: 2.0000e-03 eta: 1:16:53 time: 0.2561 data_time: 0.0112 memory: 13708 grad_norm: 6.0437 loss: 1.1812 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.1812 2023/02/18 02:48:07 - mmengine - INFO - Epoch(train) [37][ 640/1320] lr: 2.0000e-03 eta: 1:16:48 time: 0.2560 data_time: 0.0105 memory: 13708 grad_norm: 5.9667 loss: 1.1012 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1012 2023/02/18 02:48:12 - mmengine - INFO - Epoch(train) [37][ 660/1320] lr: 2.0000e-03 eta: 1:16:43 time: 0.2582 data_time: 0.0132 memory: 13708 grad_norm: 6.0241 loss: 1.0790 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0790 2023/02/18 02:48:17 - mmengine - INFO - Epoch(train) [37][ 680/1320] lr: 2.0000e-03 eta: 1:16:37 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 5.9904 loss: 1.0358 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0358 2023/02/18 02:48:22 - mmengine - INFO - Epoch(train) [37][ 700/1320] lr: 2.0000e-03 eta: 1:16:32 time: 0.2558 data_time: 0.0105 memory: 13708 grad_norm: 6.0246 loss: 1.1853 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1853 2023/02/18 02:48:28 - mmengine - INFO - Epoch(train) [37][ 720/1320] lr: 2.0000e-03 eta: 1:16:27 time: 0.2558 data_time: 0.0106 memory: 13708 grad_norm: 5.9889 loss: 1.1171 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1171 2023/02/18 02:48:33 - mmengine - INFO - Epoch(train) [37][ 740/1320] lr: 2.0000e-03 eta: 1:16:22 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 5.7949 loss: 1.1063 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1063 2023/02/18 02:48:38 - mmengine - INFO - Epoch(train) [37][ 760/1320] lr: 2.0000e-03 eta: 1:16:17 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 5.9607 loss: 1.0916 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0916 2023/02/18 02:48:43 - mmengine - INFO - Epoch(train) [37][ 780/1320] lr: 2.0000e-03 eta: 1:16:12 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 6.0234 loss: 1.1068 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1068 2023/02/18 02:48:48 - mmengine - INFO - Epoch(train) [37][ 800/1320] lr: 2.0000e-03 eta: 1:16:06 time: 0.2566 data_time: 0.0113 memory: 13708 grad_norm: 5.9527 loss: 1.2970 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 1.2970 2023/02/18 02:48:53 - mmengine - INFO - Epoch(train) [37][ 820/1320] lr: 2.0000e-03 eta: 1:16:01 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 6.1022 loss: 1.1837 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1837 2023/02/18 02:48:58 - mmengine - INFO - Epoch(train) [37][ 840/1320] lr: 2.0000e-03 eta: 1:15:56 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 5.9569 loss: 1.1058 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1058 2023/02/18 02:49:04 - mmengine - INFO - Epoch(train) [37][ 860/1320] lr: 2.0000e-03 eta: 1:15:51 time: 0.2582 data_time: 0.0120 memory: 13708 grad_norm: 5.9911 loss: 1.2494 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2494 2023/02/18 02:49:09 - mmengine - INFO - Epoch(train) [37][ 880/1320] lr: 2.0000e-03 eta: 1:15:46 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 6.0403 loss: 1.1370 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.1370 2023/02/18 02:49:14 - mmengine - INFO - Epoch(train) [37][ 900/1320] lr: 2.0000e-03 eta: 1:15:40 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 6.0261 loss: 0.9681 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9681 2023/02/18 02:49:19 - mmengine - INFO - Epoch(train) [37][ 920/1320] lr: 2.0000e-03 eta: 1:15:35 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 6.0024 loss: 1.2807 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2807 2023/02/18 02:49:24 - mmengine - INFO - Epoch(train) [37][ 940/1320] lr: 2.0000e-03 eta: 1:15:30 time: 0.2587 data_time: 0.0136 memory: 13708 grad_norm: 6.0941 loss: 1.0436 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0436 2023/02/18 02:49:29 - mmengine - INFO - Epoch(train) [37][ 960/1320] lr: 2.0000e-03 eta: 1:15:25 time: 0.2558 data_time: 0.0105 memory: 13708 grad_norm: 6.0265 loss: 0.9848 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9848 2023/02/18 02:49:34 - mmengine - INFO - Epoch(train) [37][ 980/1320] lr: 2.0000e-03 eta: 1:15:20 time: 0.2565 data_time: 0.0111 memory: 13708 grad_norm: 6.0948 loss: 1.2683 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.2683 2023/02/18 02:49:39 - mmengine - INFO - Epoch(train) [37][1000/1320] lr: 2.0000e-03 eta: 1:15:15 time: 0.2570 data_time: 0.0119 memory: 13708 grad_norm: 6.1407 loss: 1.0432 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 1.0432 2023/02/18 02:49:45 - mmengine - INFO - Epoch(train) [37][1020/1320] lr: 2.0000e-03 eta: 1:15:09 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 6.2667 loss: 1.1638 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1638 2023/02/18 02:49:50 - mmengine - INFO - Epoch(train) [37][1040/1320] lr: 2.0000e-03 eta: 1:15:04 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 6.0945 loss: 1.1371 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1371 2023/02/18 02:49:55 - mmengine - INFO - Epoch(train) [37][1060/1320] lr: 2.0000e-03 eta: 1:14:59 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 6.0206 loss: 1.2501 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2501 2023/02/18 02:50:00 - mmengine - INFO - Epoch(train) [37][1080/1320] lr: 2.0000e-03 eta: 1:14:54 time: 0.2560 data_time: 0.0106 memory: 13708 grad_norm: 5.9630 loss: 1.1258 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1258 2023/02/18 02:50:05 - mmengine - INFO - Epoch(train) [37][1100/1320] lr: 2.0000e-03 eta: 1:14:49 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 5.9331 loss: 1.2026 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2026 2023/02/18 02:50:10 - mmengine - INFO - Epoch(train) [37][1120/1320] lr: 2.0000e-03 eta: 1:14:44 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 6.0768 loss: 1.1243 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1243 2023/02/18 02:50:15 - mmengine - INFO - Epoch(train) [37][1140/1320] lr: 2.0000e-03 eta: 1:14:38 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 5.9855 loss: 1.0680 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0680 2023/02/18 02:50:20 - mmengine - INFO - Epoch(train) [37][1160/1320] lr: 2.0000e-03 eta: 1:14:33 time: 0.2564 data_time: 0.0105 memory: 13708 grad_norm: 6.0325 loss: 1.0714 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0714 2023/02/18 02:50:26 - mmengine - INFO - Epoch(train) [37][1180/1320] lr: 2.0000e-03 eta: 1:14:28 time: 0.2569 data_time: 0.0105 memory: 13708 grad_norm: 6.0822 loss: 1.2283 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 1.2283 2023/02/18 02:50:31 - mmengine - INFO - Epoch(train) [37][1200/1320] lr: 2.0000e-03 eta: 1:14:23 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 5.9271 loss: 1.1600 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1600 2023/02/18 02:50:36 - mmengine - INFO - Epoch(train) [37][1220/1320] lr: 2.0000e-03 eta: 1:14:18 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 5.9607 loss: 1.0949 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0949 2023/02/18 02:50:41 - mmengine - INFO - Epoch(train) [37][1240/1320] lr: 2.0000e-03 eta: 1:14:12 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 6.1216 loss: 1.2755 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.2755 2023/02/18 02:50:46 - mmengine - INFO - Epoch(train) [37][1260/1320] lr: 2.0000e-03 eta: 1:14:07 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 5.9916 loss: 1.1284 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1284 2023/02/18 02:50:51 - mmengine - INFO - Epoch(train) [37][1280/1320] lr: 2.0000e-03 eta: 1:14:02 time: 0.2590 data_time: 0.0135 memory: 13708 grad_norm: 6.0574 loss: 1.2085 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2085 2023/02/18 02:50:56 - mmengine - INFO - Epoch(train) [37][1300/1320] lr: 2.0000e-03 eta: 1:13:57 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 6.0365 loss: 1.2107 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2107 2023/02/18 02:51:01 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:51:01 - mmengine - INFO - Epoch(train) [37][1320/1320] lr: 2.0000e-03 eta: 1:13:52 time: 0.2512 data_time: 0.0106 memory: 13708 grad_norm: 6.1018 loss: 1.2035 top1_acc: 0.8182 top5_acc: 1.0000 loss_cls: 1.2035 2023/02/18 02:51:04 - mmengine - INFO - Epoch(val) [37][ 20/194] eta: 0:00:21 time: 0.1228 data_time: 0.0545 memory: 1818 2023/02/18 02:51:06 - mmengine - INFO - Epoch(val) [37][ 40/194] eta: 0:00:16 time: 0.0889 data_time: 0.0201 memory: 1818 2023/02/18 02:51:07 - mmengine - INFO - Epoch(val) [37][ 60/194] eta: 0:00:13 time: 0.0887 data_time: 0.0208 memory: 1818 2023/02/18 02:51:09 - mmengine - INFO - Epoch(val) [37][ 80/194] eta: 0:00:10 time: 0.0823 data_time: 0.0140 memory: 1818 2023/02/18 02:51:11 - mmengine - INFO - Epoch(val) [37][100/194] eta: 0:00:08 time: 0.0906 data_time: 0.0222 memory: 1818 2023/02/18 02:51:13 - mmengine - INFO - Epoch(val) [37][120/194] eta: 0:00:06 time: 0.0858 data_time: 0.0174 memory: 1818 2023/02/18 02:51:14 - mmengine - INFO - Epoch(val) [37][140/194] eta: 0:00:04 time: 0.0887 data_time: 0.0197 memory: 1818 2023/02/18 02:51:16 - mmengine - INFO - Epoch(val) [37][160/194] eta: 0:00:03 time: 0.0825 data_time: 0.0135 memory: 1818 2023/02/18 02:51:18 - mmengine - INFO - Epoch(val) [37][180/194] eta: 0:00:01 time: 0.0862 data_time: 0.0171 memory: 1818 2023/02/18 02:51:20 - mmengine - INFO - Epoch(val) [37][194/194] acc/top1: 0.5890 acc/top5: 0.8542 acc/mean1: 0.5246 2023/02/18 02:51:20 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_36.pth is removed 2023/02/18 02:51:21 - mmengine - INFO - The best checkpoint with 0.5890 acc/top1 at 37 epoch is saved to best_acc/top1_epoch_37.pth. 2023/02/18 02:51:27 - mmengine - INFO - Epoch(train) [38][ 20/1320] lr: 2.0000e-03 eta: 1:13:47 time: 0.2946 data_time: 0.0412 memory: 13708 grad_norm: 6.0770 loss: 1.1075 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1075 2023/02/18 02:51:32 - mmengine - INFO - Epoch(train) [38][ 40/1320] lr: 2.0000e-03 eta: 1:13:42 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 5.8962 loss: 0.9680 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.9680 2023/02/18 02:51:37 - mmengine - INFO - Epoch(train) [38][ 60/1320] lr: 2.0000e-03 eta: 1:13:36 time: 0.2557 data_time: 0.0104 memory: 13708 grad_norm: 5.9009 loss: 1.2363 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2363 2023/02/18 02:51:42 - mmengine - INFO - Epoch(train) [38][ 80/1320] lr: 2.0000e-03 eta: 1:13:31 time: 0.2560 data_time: 0.0104 memory: 13708 grad_norm: 6.1152 loss: 0.9953 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9953 2023/02/18 02:51:47 - mmengine - INFO - Epoch(train) [38][ 100/1320] lr: 2.0000e-03 eta: 1:13:26 time: 0.2559 data_time: 0.0100 memory: 13708 grad_norm: 6.0207 loss: 1.3394 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.3394 2023/02/18 02:51:52 - mmengine - INFO - Epoch(train) [38][ 120/1320] lr: 2.0000e-03 eta: 1:13:21 time: 0.2562 data_time: 0.0106 memory: 13708 grad_norm: 6.0516 loss: 1.3017 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3017 2023/02/18 02:51:58 - mmengine - INFO - Epoch(train) [38][ 140/1320] lr: 2.0000e-03 eta: 1:13:16 time: 0.2562 data_time: 0.0110 memory: 13708 grad_norm: 6.0075 loss: 1.2736 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2736 2023/02/18 02:52:03 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:52:03 - mmengine - INFO - Epoch(train) [38][ 160/1320] lr: 2.0000e-03 eta: 1:13:11 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 6.0839 loss: 1.2529 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2529 2023/02/18 02:52:08 - mmengine - INFO - Epoch(train) [38][ 180/1320] lr: 2.0000e-03 eta: 1:13:05 time: 0.2580 data_time: 0.0124 memory: 13708 grad_norm: 5.9904 loss: 0.9717 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9717 2023/02/18 02:52:13 - mmengine - INFO - Epoch(train) [38][ 200/1320] lr: 2.0000e-03 eta: 1:13:00 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 6.0211 loss: 1.0631 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0631 2023/02/18 02:52:18 - mmengine - INFO - Epoch(train) [38][ 220/1320] lr: 2.0000e-03 eta: 1:12:55 time: 0.2567 data_time: 0.0113 memory: 13708 grad_norm: 5.9213 loss: 1.2009 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2009 2023/02/18 02:52:23 - mmengine - INFO - Epoch(train) [38][ 240/1320] lr: 2.0000e-03 eta: 1:12:50 time: 0.2580 data_time: 0.0107 memory: 13708 grad_norm: 5.8565 loss: 1.0199 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0199 2023/02/18 02:52:28 - mmengine - INFO - Epoch(train) [38][ 260/1320] lr: 2.0000e-03 eta: 1:12:45 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 6.0913 loss: 1.1737 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1737 2023/02/18 02:52:33 - mmengine - INFO - Epoch(train) [38][ 280/1320] lr: 2.0000e-03 eta: 1:12:39 time: 0.2552 data_time: 0.0108 memory: 13708 grad_norm: 6.1344 loss: 0.9385 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9385 2023/02/18 02:52:39 - mmengine - INFO - Epoch(train) [38][ 300/1320] lr: 2.0000e-03 eta: 1:12:34 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 6.0576 loss: 1.0864 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0864 2023/02/18 02:52:44 - mmengine - INFO - Epoch(train) [38][ 320/1320] lr: 2.0000e-03 eta: 1:12:29 time: 0.2560 data_time: 0.0112 memory: 13708 grad_norm: 6.0971 loss: 1.1654 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1654 2023/02/18 02:52:49 - mmengine - INFO - Epoch(train) [38][ 340/1320] lr: 2.0000e-03 eta: 1:12:24 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 5.9639 loss: 1.2168 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2168 2023/02/18 02:52:54 - mmengine - INFO - Epoch(train) [38][ 360/1320] lr: 2.0000e-03 eta: 1:12:19 time: 0.2584 data_time: 0.0134 memory: 13708 grad_norm: 6.2128 loss: 1.3044 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3044 2023/02/18 02:52:59 - mmengine - INFO - Epoch(train) [38][ 380/1320] lr: 2.0000e-03 eta: 1:12:14 time: 0.2565 data_time: 0.0113 memory: 13708 grad_norm: 6.1174 loss: 1.0668 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0668 2023/02/18 02:53:04 - mmengine - INFO - Epoch(train) [38][ 400/1320] lr: 2.0000e-03 eta: 1:12:08 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 6.0504 loss: 1.1492 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1492 2023/02/18 02:53:09 - mmengine - INFO - Epoch(train) [38][ 420/1320] lr: 2.0000e-03 eta: 1:12:03 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 6.2062 loss: 1.3030 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3030 2023/02/18 02:53:15 - mmengine - INFO - Epoch(train) [38][ 440/1320] lr: 2.0000e-03 eta: 1:11:58 time: 0.2564 data_time: 0.0112 memory: 13708 grad_norm: 6.1363 loss: 1.0229 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0229 2023/02/18 02:53:20 - mmengine - INFO - Epoch(train) [38][ 460/1320] lr: 2.0000e-03 eta: 1:11:53 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 6.2404 loss: 1.1620 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1620 2023/02/18 02:53:25 - mmengine - INFO - Epoch(train) [38][ 480/1320] lr: 2.0000e-03 eta: 1:11:48 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 6.0269 loss: 1.2314 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.2314 2023/02/18 02:53:30 - mmengine - INFO - Epoch(train) [38][ 500/1320] lr: 2.0000e-03 eta: 1:11:42 time: 0.2567 data_time: 0.0116 memory: 13708 grad_norm: 6.0125 loss: 1.2681 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2681 2023/02/18 02:53:35 - mmengine - INFO - Epoch(train) [38][ 520/1320] lr: 2.0000e-03 eta: 1:11:37 time: 0.2575 data_time: 0.0128 memory: 13708 grad_norm: 6.0585 loss: 1.1891 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1891 2023/02/18 02:53:40 - mmengine - INFO - Epoch(train) [38][ 540/1320] lr: 2.0000e-03 eta: 1:11:32 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 6.1027 loss: 1.1678 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.1678 2023/02/18 02:53:45 - mmengine - INFO - Epoch(train) [38][ 560/1320] lr: 2.0000e-03 eta: 1:11:27 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 6.1035 loss: 1.2273 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2273 2023/02/18 02:53:50 - mmengine - INFO - Epoch(train) [38][ 580/1320] lr: 2.0000e-03 eta: 1:11:22 time: 0.2567 data_time: 0.0118 memory: 13708 grad_norm: 6.1805 loss: 1.0857 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0857 2023/02/18 02:53:56 - mmengine - INFO - Epoch(train) [38][ 600/1320] lr: 2.0000e-03 eta: 1:11:17 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 6.0678 loss: 1.1848 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.1848 2023/02/18 02:54:01 - mmengine - INFO - Epoch(train) [38][ 620/1320] lr: 2.0000e-03 eta: 1:11:11 time: 0.2567 data_time: 0.0117 memory: 13708 grad_norm: 6.0616 loss: 1.2387 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2387 2023/02/18 02:54:06 - mmengine - INFO - Epoch(train) [38][ 640/1320] lr: 2.0000e-03 eta: 1:11:06 time: 0.2563 data_time: 0.0115 memory: 13708 grad_norm: 6.2422 loss: 1.2802 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2802 2023/02/18 02:54:11 - mmengine - INFO - Epoch(train) [38][ 660/1320] lr: 2.0000e-03 eta: 1:11:01 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 6.0485 loss: 1.1506 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1506 2023/02/18 02:54:16 - mmengine - INFO - Epoch(train) [38][ 680/1320] lr: 2.0000e-03 eta: 1:10:56 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 6.1146 loss: 1.3200 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3200 2023/02/18 02:54:21 - mmengine - INFO - Epoch(train) [38][ 700/1320] lr: 2.0000e-03 eta: 1:10:51 time: 0.2574 data_time: 0.0106 memory: 13708 grad_norm: 6.1119 loss: 1.1323 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1323 2023/02/18 02:54:26 - mmengine - INFO - Epoch(train) [38][ 720/1320] lr: 2.0000e-03 eta: 1:10:46 time: 0.2557 data_time: 0.0104 memory: 13708 grad_norm: 6.2006 loss: 0.9955 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9955 2023/02/18 02:54:32 - mmengine - INFO - Epoch(train) [38][ 740/1320] lr: 2.0000e-03 eta: 1:10:40 time: 0.2561 data_time: 0.0113 memory: 13708 grad_norm: 6.1895 loss: 1.2465 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2465 2023/02/18 02:54:37 - mmengine - INFO - Epoch(train) [38][ 760/1320] lr: 2.0000e-03 eta: 1:10:35 time: 0.2567 data_time: 0.0106 memory: 13708 grad_norm: 6.0954 loss: 1.1695 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1695 2023/02/18 02:54:42 - mmengine - INFO - Epoch(train) [38][ 780/1320] lr: 2.0000e-03 eta: 1:10:30 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 6.2422 loss: 1.1307 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1307 2023/02/18 02:54:47 - mmengine - INFO - Epoch(train) [38][ 800/1320] lr: 2.0000e-03 eta: 1:10:25 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 6.2272 loss: 1.1322 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1322 2023/02/18 02:54:52 - mmengine - INFO - Epoch(train) [38][ 820/1320] lr: 2.0000e-03 eta: 1:10:20 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 5.9462 loss: 1.0673 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0673 2023/02/18 02:54:57 - mmengine - INFO - Epoch(train) [38][ 840/1320] lr: 2.0000e-03 eta: 1:10:14 time: 0.2563 data_time: 0.0105 memory: 13708 grad_norm: 6.0754 loss: 1.1862 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1862 2023/02/18 02:55:02 - mmengine - INFO - Epoch(train) [38][ 860/1320] lr: 2.0000e-03 eta: 1:10:09 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 6.3358 loss: 1.0142 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0142 2023/02/18 02:55:07 - mmengine - INFO - Epoch(train) [38][ 880/1320] lr: 2.0000e-03 eta: 1:10:04 time: 0.2558 data_time: 0.0106 memory: 13708 grad_norm: 6.3038 loss: 1.0895 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0895 2023/02/18 02:55:13 - mmengine - INFO - Epoch(train) [38][ 900/1320] lr: 2.0000e-03 eta: 1:09:59 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 6.2833 loss: 1.0217 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0217 2023/02/18 02:55:18 - mmengine - INFO - Epoch(train) [38][ 920/1320] lr: 2.0000e-03 eta: 1:09:54 time: 0.2563 data_time: 0.0107 memory: 13708 grad_norm: 6.2407 loss: 1.1571 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1571 2023/02/18 02:55:23 - mmengine - INFO - Epoch(train) [38][ 940/1320] lr: 2.0000e-03 eta: 1:09:49 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 6.2408 loss: 1.0051 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0051 2023/02/18 02:55:28 - mmengine - INFO - Epoch(train) [38][ 960/1320] lr: 2.0000e-03 eta: 1:09:43 time: 0.2569 data_time: 0.0114 memory: 13708 grad_norm: 6.1957 loss: 1.2174 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.2174 2023/02/18 02:55:33 - mmengine - INFO - Epoch(train) [38][ 980/1320] lr: 2.0000e-03 eta: 1:09:38 time: 0.2584 data_time: 0.0123 memory: 13708 grad_norm: 6.1389 loss: 1.0943 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0943 2023/02/18 02:55:38 - mmengine - INFO - Epoch(train) [38][1000/1320] lr: 2.0000e-03 eta: 1:09:33 time: 0.2565 data_time: 0.0113 memory: 13708 grad_norm: 6.1443 loss: 0.9635 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9635 2023/02/18 02:55:43 - mmengine - INFO - Epoch(train) [38][1020/1320] lr: 2.0000e-03 eta: 1:09:28 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 6.1251 loss: 1.1534 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1534 2023/02/18 02:55:48 - mmengine - INFO - Epoch(train) [38][1040/1320] lr: 2.0000e-03 eta: 1:09:23 time: 0.2569 data_time: 0.0123 memory: 13708 grad_norm: 6.1444 loss: 1.1488 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.1488 2023/02/18 02:55:54 - mmengine - INFO - Epoch(train) [38][1060/1320] lr: 2.0000e-03 eta: 1:09:17 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 6.3143 loss: 1.2061 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.2061 2023/02/18 02:55:59 - mmengine - INFO - Epoch(train) [38][1080/1320] lr: 2.0000e-03 eta: 1:09:12 time: 0.2552 data_time: 0.0107 memory: 13708 grad_norm: 6.2301 loss: 0.9646 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.9646 2023/02/18 02:56:04 - mmengine - INFO - Epoch(train) [38][1100/1320] lr: 2.0000e-03 eta: 1:09:07 time: 0.2557 data_time: 0.0111 memory: 13708 grad_norm: 6.1234 loss: 1.1208 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1208 2023/02/18 02:56:09 - mmengine - INFO - Epoch(train) [38][1120/1320] lr: 2.0000e-03 eta: 1:09:02 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 6.1263 loss: 1.0332 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0332 2023/02/18 02:56:14 - mmengine - INFO - Epoch(train) [38][1140/1320] lr: 2.0000e-03 eta: 1:08:57 time: 0.2571 data_time: 0.0124 memory: 13708 grad_norm: 6.4055 loss: 1.1696 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1696 2023/02/18 02:56:19 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:56:19 - mmengine - INFO - Epoch(train) [38][1160/1320] lr: 2.0000e-03 eta: 1:08:52 time: 0.2569 data_time: 0.0113 memory: 13708 grad_norm: 6.2828 loss: 1.0123 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0123 2023/02/18 02:56:24 - mmengine - INFO - Epoch(train) [38][1180/1320] lr: 2.0000e-03 eta: 1:08:46 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 6.2185 loss: 1.0730 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0730 2023/02/18 02:56:29 - mmengine - INFO - Epoch(train) [38][1200/1320] lr: 2.0000e-03 eta: 1:08:41 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 6.3720 loss: 1.0977 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0977 2023/02/18 02:56:35 - mmengine - INFO - Epoch(train) [38][1220/1320] lr: 2.0000e-03 eta: 1:08:36 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 6.0903 loss: 0.9838 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9838 2023/02/18 02:56:40 - mmengine - INFO - Epoch(train) [38][1240/1320] lr: 2.0000e-03 eta: 1:08:31 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 6.3032 loss: 1.0578 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0578 2023/02/18 02:56:45 - mmengine - INFO - Epoch(train) [38][1260/1320] lr: 2.0000e-03 eta: 1:08:26 time: 0.2567 data_time: 0.0109 memory: 13708 grad_norm: 6.1626 loss: 1.1905 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1905 2023/02/18 02:56:50 - mmengine - INFO - Epoch(train) [38][1280/1320] lr: 2.0000e-03 eta: 1:08:21 time: 0.2567 data_time: 0.0108 memory: 13708 grad_norm: 6.2254 loss: 1.1364 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1364 2023/02/18 02:56:55 - mmengine - INFO - Epoch(train) [38][1300/1320] lr: 2.0000e-03 eta: 1:08:15 time: 0.2570 data_time: 0.0121 memory: 13708 grad_norm: 6.3341 loss: 1.1512 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1512 2023/02/18 02:57:00 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 02:57:00 - mmengine - INFO - Epoch(train) [38][1320/1320] lr: 2.0000e-03 eta: 1:08:10 time: 0.2518 data_time: 0.0108 memory: 13708 grad_norm: 6.1331 loss: 1.0405 top1_acc: 0.1818 top5_acc: 0.8182 loss_cls: 1.0405 2023/02/18 02:57:03 - mmengine - INFO - Epoch(val) [38][ 20/194] eta: 0:00:20 time: 0.1206 data_time: 0.0518 memory: 1818 2023/02/18 02:57:04 - mmengine - INFO - Epoch(val) [38][ 40/194] eta: 0:00:16 time: 0.0881 data_time: 0.0197 memory: 1818 2023/02/18 02:57:06 - mmengine - INFO - Epoch(val) [38][ 60/194] eta: 0:00:13 time: 0.0890 data_time: 0.0203 memory: 1818 2023/02/18 02:57:08 - mmengine - INFO - Epoch(val) [38][ 80/194] eta: 0:00:10 time: 0.0861 data_time: 0.0176 memory: 1818 2023/02/18 02:57:10 - mmengine - INFO - Epoch(val) [38][100/194] eta: 0:00:08 time: 0.0885 data_time: 0.0196 memory: 1818 2023/02/18 02:57:11 - mmengine - INFO - Epoch(val) [38][120/194] eta: 0:00:06 time: 0.0850 data_time: 0.0165 memory: 1818 2023/02/18 02:57:13 - mmengine - INFO - Epoch(val) [38][140/194] eta: 0:00:04 time: 0.0908 data_time: 0.0218 memory: 1818 2023/02/18 02:57:15 - mmengine - INFO - Epoch(val) [38][160/194] eta: 0:00:03 time: 0.0813 data_time: 0.0127 memory: 1818 2023/02/18 02:57:17 - mmengine - INFO - Epoch(val) [38][180/194] eta: 0:00:01 time: 0.0885 data_time: 0.0200 memory: 1818 2023/02/18 02:57:19 - mmengine - INFO - Epoch(val) [38][194/194] acc/top1: 0.5870 acc/top5: 0.8523 acc/mean1: 0.5220 2023/02/18 02:57:25 - mmengine - INFO - Epoch(train) [39][ 20/1320] lr: 2.0000e-03 eta: 1:08:05 time: 0.2975 data_time: 0.0420 memory: 13708 grad_norm: 6.2425 loss: 1.1147 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1147 2023/02/18 02:57:30 - mmengine - INFO - Epoch(train) [39][ 40/1320] lr: 2.0000e-03 eta: 1:08:00 time: 0.2565 data_time: 0.0112 memory: 13708 grad_norm: 5.9952 loss: 0.8975 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8975 2023/02/18 02:57:35 - mmengine - INFO - Epoch(train) [39][ 60/1320] lr: 2.0000e-03 eta: 1:07:55 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 6.2096 loss: 1.1083 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1083 2023/02/18 02:57:40 - mmengine - INFO - Epoch(train) [39][ 80/1320] lr: 2.0000e-03 eta: 1:07:50 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 6.1685 loss: 1.0696 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0696 2023/02/18 02:57:45 - mmengine - INFO - Epoch(train) [39][ 100/1320] lr: 2.0000e-03 eta: 1:07:45 time: 0.2564 data_time: 0.0110 memory: 13708 grad_norm: 6.2080 loss: 1.1242 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1242 2023/02/18 02:57:50 - mmengine - INFO - Epoch(train) [39][ 120/1320] lr: 2.0000e-03 eta: 1:07:39 time: 0.2567 data_time: 0.0114 memory: 13708 grad_norm: 6.0989 loss: 1.1987 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1987 2023/02/18 02:57:55 - mmengine - INFO - Epoch(train) [39][ 140/1320] lr: 2.0000e-03 eta: 1:07:34 time: 0.2554 data_time: 0.0103 memory: 13708 grad_norm: 6.0754 loss: 1.0800 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0800 2023/02/18 02:58:01 - mmengine - INFO - Epoch(train) [39][ 160/1320] lr: 2.0000e-03 eta: 1:07:29 time: 0.2554 data_time: 0.0106 memory: 13708 grad_norm: 6.1465 loss: 1.0976 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.0976 2023/02/18 02:58:06 - mmengine - INFO - Epoch(train) [39][ 180/1320] lr: 2.0000e-03 eta: 1:07:24 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 6.1840 loss: 1.1644 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1644 2023/02/18 02:58:11 - mmengine - INFO - Epoch(train) [39][ 200/1320] lr: 2.0000e-03 eta: 1:07:19 time: 0.2556 data_time: 0.0110 memory: 13708 grad_norm: 6.2379 loss: 1.0915 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0915 2023/02/18 02:58:16 - mmengine - INFO - Epoch(train) [39][ 220/1320] lr: 2.0000e-03 eta: 1:07:13 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 6.1568 loss: 1.0841 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0841 2023/02/18 02:58:21 - mmengine - INFO - Epoch(train) [39][ 240/1320] lr: 2.0000e-03 eta: 1:07:08 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 6.0087 loss: 1.0300 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0300 2023/02/18 02:58:26 - mmengine - INFO - Epoch(train) [39][ 260/1320] lr: 2.0000e-03 eta: 1:07:03 time: 0.2560 data_time: 0.0114 memory: 13708 grad_norm: 6.2107 loss: 1.0187 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0187 2023/02/18 02:58:31 - mmengine - INFO - Epoch(train) [39][ 280/1320] lr: 2.0000e-03 eta: 1:06:58 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 6.1918 loss: 0.9500 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9500 2023/02/18 02:58:36 - mmengine - INFO - Epoch(train) [39][ 300/1320] lr: 2.0000e-03 eta: 1:06:53 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 6.3290 loss: 1.2885 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2885 2023/02/18 02:58:42 - mmengine - INFO - Epoch(train) [39][ 320/1320] lr: 2.0000e-03 eta: 1:06:48 time: 0.2567 data_time: 0.0108 memory: 13708 grad_norm: 6.2931 loss: 1.1570 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1570 2023/02/18 02:58:47 - mmengine - INFO - Epoch(train) [39][ 340/1320] lr: 2.0000e-03 eta: 1:06:42 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 6.2233 loss: 1.1215 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1215 2023/02/18 02:58:52 - mmengine - INFO - Epoch(train) [39][ 360/1320] lr: 2.0000e-03 eta: 1:06:37 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 6.2548 loss: 1.0834 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0834 2023/02/18 02:58:57 - mmengine - INFO - Epoch(train) [39][ 380/1320] lr: 2.0000e-03 eta: 1:06:32 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 6.1995 loss: 1.2126 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2126 2023/02/18 02:59:02 - mmengine - INFO - Epoch(train) [39][ 400/1320] lr: 2.0000e-03 eta: 1:06:27 time: 0.2552 data_time: 0.0106 memory: 13708 grad_norm: 6.4643 loss: 0.9871 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9871 2023/02/18 02:59:07 - mmengine - INFO - Epoch(train) [39][ 420/1320] lr: 2.0000e-03 eta: 1:06:22 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 6.3947 loss: 1.1390 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.1390 2023/02/18 02:59:12 - mmengine - INFO - Epoch(train) [39][ 440/1320] lr: 2.0000e-03 eta: 1:06:16 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 6.4129 loss: 1.1087 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1087 2023/02/18 02:59:17 - mmengine - INFO - Epoch(train) [39][ 460/1320] lr: 2.0000e-03 eta: 1:06:11 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 6.2987 loss: 1.2093 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2093 2023/02/18 02:59:23 - mmengine - INFO - Epoch(train) [39][ 480/1320] lr: 2.0000e-03 eta: 1:06:06 time: 0.2562 data_time: 0.0106 memory: 13708 grad_norm: 6.2136 loss: 1.0804 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.0804 2023/02/18 02:59:28 - mmengine - INFO - Epoch(train) [39][ 500/1320] lr: 2.0000e-03 eta: 1:06:01 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 6.1906 loss: 1.0808 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0808 2023/02/18 02:59:33 - mmengine - INFO - Epoch(train) [39][ 520/1320] lr: 2.0000e-03 eta: 1:05:56 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 6.0107 loss: 1.1235 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1235 2023/02/18 02:59:38 - mmengine - INFO - Epoch(train) [39][ 540/1320] lr: 2.0000e-03 eta: 1:05:51 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 6.3952 loss: 1.1080 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1080 2023/02/18 02:59:43 - mmengine - INFO - Epoch(train) [39][ 560/1320] lr: 2.0000e-03 eta: 1:05:45 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 6.3877 loss: 1.0157 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0157 2023/02/18 02:59:48 - mmengine - INFO - Epoch(train) [39][ 580/1320] lr: 2.0000e-03 eta: 1:05:40 time: 0.2571 data_time: 0.0117 memory: 13708 grad_norm: 6.2646 loss: 1.2274 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2274 2023/02/18 02:59:53 - mmengine - INFO - Epoch(train) [39][ 600/1320] lr: 2.0000e-03 eta: 1:05:35 time: 0.2576 data_time: 0.0127 memory: 13708 grad_norm: 6.4663 loss: 1.2276 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2276 2023/02/18 02:59:58 - mmengine - INFO - Epoch(train) [39][ 620/1320] lr: 2.0000e-03 eta: 1:05:30 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 6.4176 loss: 1.1824 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.1824 2023/02/18 03:00:04 - mmengine - INFO - Epoch(train) [39][ 640/1320] lr: 2.0000e-03 eta: 1:05:25 time: 0.2567 data_time: 0.0113 memory: 13708 grad_norm: 6.3412 loss: 1.2247 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2247 2023/02/18 03:00:09 - mmengine - INFO - Epoch(train) [39][ 660/1320] lr: 2.0000e-03 eta: 1:05:20 time: 0.2563 data_time: 0.0105 memory: 13708 grad_norm: 6.3207 loss: 1.2392 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.2392 2023/02/18 03:00:14 - mmengine - INFO - Epoch(train) [39][ 680/1320] lr: 2.0000e-03 eta: 1:05:14 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 6.3064 loss: 1.0742 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0742 2023/02/18 03:00:19 - mmengine - INFO - Epoch(train) [39][ 700/1320] lr: 2.0000e-03 eta: 1:05:09 time: 0.2566 data_time: 0.0108 memory: 13708 grad_norm: 6.4117 loss: 1.0330 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.0330 2023/02/18 03:00:24 - mmengine - INFO - Epoch(train) [39][ 720/1320] lr: 2.0000e-03 eta: 1:05:04 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 6.3653 loss: 1.1382 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1382 2023/02/18 03:00:29 - mmengine - INFO - Epoch(train) [39][ 740/1320] lr: 2.0000e-03 eta: 1:04:59 time: 0.2564 data_time: 0.0110 memory: 13708 grad_norm: 6.1275 loss: 1.1595 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1595 2023/02/18 03:00:34 - mmengine - INFO - Epoch(train) [39][ 760/1320] lr: 2.0000e-03 eta: 1:04:54 time: 0.2560 data_time: 0.0112 memory: 13708 grad_norm: 6.4103 loss: 1.1243 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1243 2023/02/18 03:00:39 - mmengine - INFO - Epoch(train) [39][ 780/1320] lr: 2.0000e-03 eta: 1:04:48 time: 0.2581 data_time: 0.0131 memory: 13708 grad_norm: 6.4745 loss: 1.0828 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0828 2023/02/18 03:00:45 - mmengine - INFO - Epoch(train) [39][ 800/1320] lr: 2.0000e-03 eta: 1:04:43 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 6.5950 loss: 1.3174 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.3174 2023/02/18 03:00:50 - mmengine - INFO - Epoch(train) [39][ 820/1320] lr: 2.0000e-03 eta: 1:04:38 time: 0.2566 data_time: 0.0110 memory: 13708 grad_norm: 6.3465 loss: 1.1134 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1134 2023/02/18 03:00:55 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:00:55 - mmengine - INFO - Epoch(train) [39][ 840/1320] lr: 2.0000e-03 eta: 1:04:33 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 6.2165 loss: 1.0382 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.0382 2023/02/18 03:01:00 - mmengine - INFO - Epoch(train) [39][ 860/1320] lr: 2.0000e-03 eta: 1:04:28 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 6.3492 loss: 1.1603 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1603 2023/02/18 03:01:05 - mmengine - INFO - Epoch(train) [39][ 880/1320] lr: 2.0000e-03 eta: 1:04:23 time: 0.2556 data_time: 0.0103 memory: 13708 grad_norm: 6.2884 loss: 1.0255 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0255 2023/02/18 03:01:10 - mmengine - INFO - Epoch(train) [39][ 900/1320] lr: 2.0000e-03 eta: 1:04:17 time: 0.2569 data_time: 0.0118 memory: 13708 grad_norm: 6.2833 loss: 1.2117 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2117 2023/02/18 03:01:15 - mmengine - INFO - Epoch(train) [39][ 920/1320] lr: 2.0000e-03 eta: 1:04:12 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 6.3473 loss: 1.1978 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1978 2023/02/18 03:01:20 - mmengine - INFO - Epoch(train) [39][ 940/1320] lr: 2.0000e-03 eta: 1:04:07 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 6.3124 loss: 1.0488 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.0488 2023/02/18 03:01:26 - mmengine - INFO - Epoch(train) [39][ 960/1320] lr: 2.0000e-03 eta: 1:04:02 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 6.3758 loss: 1.0029 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.0029 2023/02/18 03:01:31 - mmengine - INFO - Epoch(train) [39][ 980/1320] lr: 2.0000e-03 eta: 1:03:57 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 6.6222 loss: 1.2348 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.2348 2023/02/18 03:01:36 - mmengine - INFO - Epoch(train) [39][1000/1320] lr: 2.0000e-03 eta: 1:03:52 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 6.5516 loss: 1.0945 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0945 2023/02/18 03:01:41 - mmengine - INFO - Epoch(train) [39][1020/1320] lr: 2.0000e-03 eta: 1:03:46 time: 0.2572 data_time: 0.0119 memory: 13708 grad_norm: 6.6627 loss: 1.0825 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0825 2023/02/18 03:01:46 - mmengine - INFO - Epoch(train) [39][1040/1320] lr: 2.0000e-03 eta: 1:03:41 time: 0.2560 data_time: 0.0103 memory: 13708 grad_norm: 6.4955 loss: 1.1736 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1736 2023/02/18 03:01:51 - mmengine - INFO - Epoch(train) [39][1060/1320] lr: 2.0000e-03 eta: 1:03:36 time: 0.2563 data_time: 0.0112 memory: 13708 grad_norm: 6.5135 loss: 1.1136 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1136 2023/02/18 03:01:56 - mmengine - INFO - Epoch(train) [39][1080/1320] lr: 2.0000e-03 eta: 1:03:31 time: 0.2562 data_time: 0.0104 memory: 13708 grad_norm: 6.3361 loss: 1.1472 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1472 2023/02/18 03:02:01 - mmengine - INFO - Epoch(train) [39][1100/1320] lr: 2.0000e-03 eta: 1:03:26 time: 0.2555 data_time: 0.0106 memory: 13708 grad_norm: 6.2293 loss: 1.1635 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1635 2023/02/18 03:02:07 - mmengine - INFO - Epoch(train) [39][1120/1320] lr: 2.0000e-03 eta: 1:03:20 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 6.3365 loss: 1.1166 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1166 2023/02/18 03:02:12 - mmengine - INFO - Epoch(train) [39][1140/1320] lr: 2.0000e-03 eta: 1:03:15 time: 0.2563 data_time: 0.0106 memory: 13708 grad_norm: 6.2910 loss: 0.9405 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9405 2023/02/18 03:02:17 - mmengine - INFO - Epoch(train) [39][1160/1320] lr: 2.0000e-03 eta: 1:03:10 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 6.4636 loss: 1.1674 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1674 2023/02/18 03:02:22 - mmengine - INFO - Epoch(train) [39][1180/1320] lr: 2.0000e-03 eta: 1:03:05 time: 0.2568 data_time: 0.0114 memory: 13708 grad_norm: 6.6570 loss: 1.1408 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1408 2023/02/18 03:02:27 - mmengine - INFO - Epoch(train) [39][1200/1320] lr: 2.0000e-03 eta: 1:03:00 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 6.3413 loss: 1.1480 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1480 2023/02/18 03:02:32 - mmengine - INFO - Epoch(train) [39][1220/1320] lr: 2.0000e-03 eta: 1:02:55 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 6.4615 loss: 1.1047 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1047 2023/02/18 03:02:37 - mmengine - INFO - Epoch(train) [39][1240/1320] lr: 2.0000e-03 eta: 1:02:49 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 6.4279 loss: 1.0817 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.0817 2023/02/18 03:02:44 - mmengine - INFO - Epoch(train) [39][1260/1320] lr: 2.0000e-03 eta: 1:02:45 time: 0.3145 data_time: 0.0107 memory: 13708 grad_norm: 6.4054 loss: 1.3115 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.3115 2023/02/18 03:02:49 - mmengine - INFO - Epoch(train) [39][1280/1320] lr: 2.0000e-03 eta: 1:02:39 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 6.4007 loss: 1.0568 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0568 2023/02/18 03:02:54 - mmengine - INFO - Epoch(train) [39][1300/1320] lr: 2.0000e-03 eta: 1:02:34 time: 0.2559 data_time: 0.0113 memory: 13708 grad_norm: 6.3485 loss: 1.2552 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2552 2023/02/18 03:02:59 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:02:59 - mmengine - INFO - Epoch(train) [39][1320/1320] lr: 2.0000e-03 eta: 1:02:29 time: 0.2521 data_time: 0.0104 memory: 13708 grad_norm: 6.4891 loss: 1.2791 top1_acc: 0.4545 top5_acc: 0.7273 loss_cls: 1.2791 2023/02/18 03:02:59 - mmengine - INFO - Saving checkpoint at 39 epochs 2023/02/18 03:03:03 - mmengine - INFO - Epoch(val) [39][ 20/194] eta: 0:00:22 time: 0.1298 data_time: 0.0610 memory: 1818 2023/02/18 03:03:04 - mmengine - INFO - Epoch(val) [39][ 40/194] eta: 0:00:16 time: 0.0877 data_time: 0.0197 memory: 1818 2023/02/18 03:03:06 - mmengine - INFO - Epoch(val) [39][ 60/194] eta: 0:00:13 time: 0.0886 data_time: 0.0195 memory: 1818 2023/02/18 03:03:08 - mmengine - INFO - Epoch(val) [39][ 80/194] eta: 0:00:11 time: 0.0925 data_time: 0.0238 memory: 1818 2023/02/18 03:03:10 - mmengine - INFO - Epoch(val) [39][100/194] eta: 0:00:09 time: 0.0857 data_time: 0.0174 memory: 1818 2023/02/18 03:03:12 - mmengine - INFO - Epoch(val) [39][120/194] eta: 0:00:07 time: 0.0876 data_time: 0.0192 memory: 1818 2023/02/18 03:03:13 - mmengine - INFO - Epoch(val) [39][140/194] eta: 0:00:05 time: 0.0898 data_time: 0.0213 memory: 1818 2023/02/18 03:03:15 - mmengine - INFO - Epoch(val) [39][160/194] eta: 0:00:03 time: 0.0807 data_time: 0.0123 memory: 1818 2023/02/18 03:03:17 - mmengine - INFO - Epoch(val) [39][180/194] eta: 0:00:01 time: 0.0826 data_time: 0.0167 memory: 1818 2023/02/18 03:03:18 - mmengine - INFO - Epoch(val) [39][194/194] acc/top1: 0.5860 acc/top5: 0.8531 acc/mean1: 0.5252 2023/02/18 03:03:24 - mmengine - INFO - Epoch(train) [40][ 20/1320] lr: 2.0000e-03 eta: 1:02:24 time: 0.3009 data_time: 0.0395 memory: 13708 grad_norm: 6.2640 loss: 1.0886 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0886 2023/02/18 03:03:29 - mmengine - INFO - Epoch(train) [40][ 40/1320] lr: 2.0000e-03 eta: 1:02:19 time: 0.2569 data_time: 0.0109 memory: 13708 grad_norm: 6.2675 loss: 1.1198 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1198 2023/02/18 03:03:35 - mmengine - INFO - Epoch(train) [40][ 60/1320] lr: 2.0000e-03 eta: 1:02:14 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 6.4004 loss: 1.1808 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1808 2023/02/18 03:03:40 - mmengine - INFO - Epoch(train) [40][ 80/1320] lr: 2.0000e-03 eta: 1:02:09 time: 0.2560 data_time: 0.0111 memory: 13708 grad_norm: 6.4559 loss: 1.1652 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1652 2023/02/18 03:03:45 - mmengine - INFO - Epoch(train) [40][ 100/1320] lr: 2.0000e-03 eta: 1:02:03 time: 0.2570 data_time: 0.0106 memory: 13708 grad_norm: 6.4099 loss: 0.9688 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9688 2023/02/18 03:03:50 - mmengine - INFO - Epoch(train) [40][ 120/1320] lr: 2.0000e-03 eta: 1:01:58 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 6.3219 loss: 1.0116 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0116 2023/02/18 03:03:55 - mmengine - INFO - Epoch(train) [40][ 140/1320] lr: 2.0000e-03 eta: 1:01:53 time: 0.2592 data_time: 0.0130 memory: 13708 grad_norm: 6.2207 loss: 1.1644 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1644 2023/02/18 03:04:00 - mmengine - INFO - Epoch(train) [40][ 160/1320] lr: 2.0000e-03 eta: 1:01:48 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 6.1382 loss: 0.9036 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9036 2023/02/18 03:04:05 - mmengine - INFO - Epoch(train) [40][ 180/1320] lr: 2.0000e-03 eta: 1:01:43 time: 0.2569 data_time: 0.0117 memory: 13708 grad_norm: 6.4070 loss: 1.1697 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.1697 2023/02/18 03:04:11 - mmengine - INFO - Epoch(train) [40][ 200/1320] lr: 2.0000e-03 eta: 1:01:38 time: 0.2555 data_time: 0.0102 memory: 13708 grad_norm: 6.4852 loss: 1.1923 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1923 2023/02/18 03:04:16 - mmengine - INFO - Epoch(train) [40][ 220/1320] lr: 2.0000e-03 eta: 1:01:32 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 6.4513 loss: 1.0883 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0883 2023/02/18 03:04:21 - mmengine - INFO - Epoch(train) [40][ 240/1320] lr: 2.0000e-03 eta: 1:01:27 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 6.3733 loss: 0.9820 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9820 2023/02/18 03:04:26 - mmengine - INFO - Epoch(train) [40][ 260/1320] lr: 2.0000e-03 eta: 1:01:22 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 6.4381 loss: 1.0337 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0337 2023/02/18 03:04:31 - mmengine - INFO - Epoch(train) [40][ 280/1320] lr: 2.0000e-03 eta: 1:01:17 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 6.5017 loss: 1.1460 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1460 2023/02/18 03:04:36 - mmengine - INFO - Epoch(train) [40][ 300/1320] lr: 2.0000e-03 eta: 1:01:12 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 6.2976 loss: 1.0469 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0469 2023/02/18 03:04:41 - mmengine - INFO - Epoch(train) [40][ 320/1320] lr: 2.0000e-03 eta: 1:01:06 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 6.4781 loss: 1.2331 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2331 2023/02/18 03:04:46 - mmengine - INFO - Epoch(train) [40][ 340/1320] lr: 2.0000e-03 eta: 1:01:01 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 6.1595 loss: 1.1829 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.1829 2023/02/18 03:04:52 - mmengine - INFO - Epoch(train) [40][ 360/1320] lr: 2.0000e-03 eta: 1:00:56 time: 0.2562 data_time: 0.0103 memory: 13708 grad_norm: 6.3583 loss: 0.9890 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9890 2023/02/18 03:04:57 - mmengine - INFO - Epoch(train) [40][ 380/1320] lr: 2.0000e-03 eta: 1:00:51 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 6.4005 loss: 1.0989 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0989 2023/02/18 03:05:02 - mmengine - INFO - Epoch(train) [40][ 400/1320] lr: 2.0000e-03 eta: 1:00:46 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 6.5095 loss: 1.1820 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1820 2023/02/18 03:05:07 - mmengine - INFO - Epoch(train) [40][ 420/1320] lr: 2.0000e-03 eta: 1:00:41 time: 0.2568 data_time: 0.0103 memory: 13708 grad_norm: 6.5734 loss: 0.9423 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9423 2023/02/18 03:05:12 - mmengine - INFO - Epoch(train) [40][ 440/1320] lr: 2.0000e-03 eta: 1:00:35 time: 0.2569 data_time: 0.0110 memory: 13708 grad_norm: 6.4426 loss: 1.2499 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2499 2023/02/18 03:05:17 - mmengine - INFO - Epoch(train) [40][ 460/1320] lr: 2.0000e-03 eta: 1:00:30 time: 0.2553 data_time: 0.0105 memory: 13708 grad_norm: 6.6622 loss: 1.0395 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0395 2023/02/18 03:05:22 - mmengine - INFO - Epoch(train) [40][ 480/1320] lr: 2.0000e-03 eta: 1:00:25 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 6.5805 loss: 1.0934 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0934 2023/02/18 03:05:27 - mmengine - INFO - Epoch(train) [40][ 500/1320] lr: 2.0000e-03 eta: 1:00:20 time: 0.2566 data_time: 0.0109 memory: 13708 grad_norm: 6.4634 loss: 1.0265 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0265 2023/02/18 03:05:33 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:05:33 - mmengine - INFO - Epoch(train) [40][ 520/1320] lr: 2.0000e-03 eta: 1:00:15 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 6.5617 loss: 1.0049 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0049 2023/02/18 03:05:38 - mmengine - INFO - Epoch(train) [40][ 540/1320] lr: 2.0000e-03 eta: 1:00:10 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 6.2474 loss: 1.1104 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1104 2023/02/18 03:05:43 - mmengine - INFO - Epoch(train) [40][ 560/1320] lr: 2.0000e-03 eta: 1:00:04 time: 0.2564 data_time: 0.0108 memory: 13708 grad_norm: 6.6062 loss: 1.0865 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0865 2023/02/18 03:05:48 - mmengine - INFO - Epoch(train) [40][ 580/1320] lr: 2.0000e-03 eta: 0:59:59 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 6.7304 loss: 1.0995 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.0995 2023/02/18 03:05:53 - mmengine - INFO - Epoch(train) [40][ 600/1320] lr: 2.0000e-03 eta: 0:59:54 time: 0.2567 data_time: 0.0116 memory: 13708 grad_norm: 6.4057 loss: 1.0109 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0109 2023/02/18 03:05:58 - mmengine - INFO - Epoch(train) [40][ 620/1320] lr: 2.0000e-03 eta: 0:59:49 time: 0.2561 data_time: 0.0105 memory: 13708 grad_norm: 6.3717 loss: 1.1613 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.1613 2023/02/18 03:06:03 - mmengine - INFO - Epoch(train) [40][ 640/1320] lr: 2.0000e-03 eta: 0:59:44 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 6.5228 loss: 1.2499 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2499 2023/02/18 03:06:08 - mmengine - INFO - Epoch(train) [40][ 660/1320] lr: 2.0000e-03 eta: 0:59:38 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 6.4732 loss: 1.2236 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2236 2023/02/18 03:06:14 - mmengine - INFO - Epoch(train) [40][ 680/1320] lr: 2.0000e-03 eta: 0:59:33 time: 0.2564 data_time: 0.0115 memory: 13708 grad_norm: 6.3618 loss: 1.1543 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1543 2023/02/18 03:06:19 - mmengine - INFO - Epoch(train) [40][ 700/1320] lr: 2.0000e-03 eta: 0:59:28 time: 0.2576 data_time: 0.0121 memory: 13708 grad_norm: 6.3144 loss: 1.1453 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.1453 2023/02/18 03:06:24 - mmengine - INFO - Epoch(train) [40][ 720/1320] lr: 2.0000e-03 eta: 0:59:23 time: 0.2564 data_time: 0.0108 memory: 13708 grad_norm: 6.3167 loss: 1.0482 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0482 2023/02/18 03:06:29 - mmengine - INFO - Epoch(train) [40][ 740/1320] lr: 2.0000e-03 eta: 0:59:18 time: 0.2573 data_time: 0.0114 memory: 13708 grad_norm: 6.4346 loss: 1.0241 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.0241 2023/02/18 03:06:34 - mmengine - INFO - Epoch(train) [40][ 760/1320] lr: 2.0000e-03 eta: 0:59:13 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 6.5461 loss: 1.2388 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2388 2023/02/18 03:06:39 - mmengine - INFO - Epoch(train) [40][ 780/1320] lr: 2.0000e-03 eta: 0:59:07 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 6.4868 loss: 1.2335 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2335 2023/02/18 03:06:44 - mmengine - INFO - Epoch(train) [40][ 800/1320] lr: 2.0000e-03 eta: 0:59:02 time: 0.2560 data_time: 0.0103 memory: 13708 grad_norm: 6.4724 loss: 1.1914 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1914 2023/02/18 03:06:50 - mmengine - INFO - Epoch(train) [40][ 820/1320] lr: 2.0000e-03 eta: 0:58:57 time: 0.2562 data_time: 0.0115 memory: 13708 grad_norm: 6.5087 loss: 1.1910 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1910 2023/02/18 03:06:55 - mmengine - INFO - Epoch(train) [40][ 840/1320] lr: 2.0000e-03 eta: 0:58:52 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 6.5425 loss: 1.0443 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0443 2023/02/18 03:07:00 - mmengine - INFO - Epoch(train) [40][ 860/1320] lr: 2.0000e-03 eta: 0:58:47 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 6.7648 loss: 1.1350 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1350 2023/02/18 03:07:05 - mmengine - INFO - Epoch(train) [40][ 880/1320] lr: 2.0000e-03 eta: 0:58:42 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 6.6176 loss: 1.0780 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0780 2023/02/18 03:07:10 - mmengine - INFO - Epoch(train) [40][ 900/1320] lr: 2.0000e-03 eta: 0:58:36 time: 0.2555 data_time: 0.0100 memory: 13708 grad_norm: 6.6143 loss: 1.0883 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0883 2023/02/18 03:07:15 - mmengine - INFO - Epoch(train) [40][ 920/1320] lr: 2.0000e-03 eta: 0:58:31 time: 0.2572 data_time: 0.0116 memory: 13708 grad_norm: 6.6846 loss: 1.2807 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2807 2023/02/18 03:07:20 - mmengine - INFO - Epoch(train) [40][ 940/1320] lr: 2.0000e-03 eta: 0:58:26 time: 0.2570 data_time: 0.0112 memory: 13708 grad_norm: 6.4679 loss: 1.2023 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.2023 2023/02/18 03:07:25 - mmengine - INFO - Epoch(train) [40][ 960/1320] lr: 2.0000e-03 eta: 0:58:21 time: 0.2566 data_time: 0.0115 memory: 13708 grad_norm: 6.4648 loss: 1.1301 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1301 2023/02/18 03:07:31 - mmengine - INFO - Epoch(train) [40][ 980/1320] lr: 2.0000e-03 eta: 0:58:16 time: 0.2582 data_time: 0.0107 memory: 13708 grad_norm: 6.6509 loss: 1.1849 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1849 2023/02/18 03:07:36 - mmengine - INFO - Epoch(train) [40][1000/1320] lr: 2.0000e-03 eta: 0:58:11 time: 0.2558 data_time: 0.0105 memory: 13708 grad_norm: 6.6573 loss: 1.0256 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0256 2023/02/18 03:07:41 - mmengine - INFO - Epoch(train) [40][1020/1320] lr: 2.0000e-03 eta: 0:58:05 time: 0.2564 data_time: 0.0112 memory: 13708 grad_norm: 6.6472 loss: 1.1490 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1490 2023/02/18 03:07:46 - mmengine - INFO - Epoch(train) [40][1040/1320] lr: 2.0000e-03 eta: 0:58:00 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 6.8144 loss: 1.2042 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2042 2023/02/18 03:07:51 - mmengine - INFO - Epoch(train) [40][1060/1320] lr: 2.0000e-03 eta: 0:57:55 time: 0.2568 data_time: 0.0108 memory: 13708 grad_norm: 6.5160 loss: 1.0334 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0334 2023/02/18 03:07:56 - mmengine - INFO - Epoch(train) [40][1080/1320] lr: 2.0000e-03 eta: 0:57:50 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 6.5214 loss: 1.1756 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1756 2023/02/18 03:08:01 - mmengine - INFO - Epoch(train) [40][1100/1320] lr: 2.0000e-03 eta: 0:57:45 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 6.6027 loss: 1.0861 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.0861 2023/02/18 03:08:07 - mmengine - INFO - Epoch(train) [40][1120/1320] lr: 2.0000e-03 eta: 0:57:39 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 6.4276 loss: 1.0888 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.0888 2023/02/18 03:08:12 - mmengine - INFO - Epoch(train) [40][1140/1320] lr: 2.0000e-03 eta: 0:57:34 time: 0.2567 data_time: 0.0106 memory: 13708 grad_norm: 6.5513 loss: 1.0695 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0695 2023/02/18 03:08:17 - mmengine - INFO - Epoch(train) [40][1160/1320] lr: 2.0000e-03 eta: 0:57:29 time: 0.2556 data_time: 0.0109 memory: 13708 grad_norm: 6.6074 loss: 1.2522 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.2522 2023/02/18 03:08:22 - mmengine - INFO - Epoch(train) [40][1180/1320] lr: 2.0000e-03 eta: 0:57:24 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 6.5552 loss: 1.2364 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2364 2023/02/18 03:08:27 - mmengine - INFO - Epoch(train) [40][1200/1320] lr: 2.0000e-03 eta: 0:57:19 time: 0.2566 data_time: 0.0109 memory: 13708 grad_norm: 6.4036 loss: 1.2384 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2384 2023/02/18 03:08:32 - mmengine - INFO - Epoch(train) [40][1220/1320] lr: 2.0000e-03 eta: 0:57:14 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 6.3859 loss: 1.2134 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2134 2023/02/18 03:08:37 - mmengine - INFO - Epoch(train) [40][1240/1320] lr: 2.0000e-03 eta: 0:57:08 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 6.7739 loss: 1.0385 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0385 2023/02/18 03:08:42 - mmengine - INFO - Epoch(train) [40][1260/1320] lr: 2.0000e-03 eta: 0:57:03 time: 0.2568 data_time: 0.0110 memory: 13708 grad_norm: 6.6034 loss: 1.1267 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.1267 2023/02/18 03:08:48 - mmengine - INFO - Epoch(train) [40][1280/1320] lr: 2.0000e-03 eta: 0:56:58 time: 0.2568 data_time: 0.0103 memory: 13708 grad_norm: 6.3769 loss: 1.1063 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.1063 2023/02/18 03:08:53 - mmengine - INFO - Epoch(train) [40][1300/1320] lr: 2.0000e-03 eta: 0:56:53 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 6.4969 loss: 1.0434 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0434 2023/02/18 03:08:58 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:08:58 - mmengine - INFO - Epoch(train) [40][1320/1320] lr: 2.0000e-03 eta: 0:56:48 time: 0.2525 data_time: 0.0113 memory: 13708 grad_norm: 6.6798 loss: 1.0460 top1_acc: 0.7273 top5_acc: 0.8182 loss_cls: 1.0460 2023/02/18 03:09:00 - mmengine - INFO - Epoch(val) [40][ 20/194] eta: 0:00:21 time: 0.1238 data_time: 0.0551 memory: 1818 2023/02/18 03:09:02 - mmengine - INFO - Epoch(val) [40][ 40/194] eta: 0:00:16 time: 0.0870 data_time: 0.0182 memory: 1818 2023/02/18 03:09:04 - mmengine - INFO - Epoch(val) [40][ 60/194] eta: 0:00:13 time: 0.0903 data_time: 0.0211 memory: 1818 2023/02/18 03:09:05 - mmengine - INFO - Epoch(val) [40][ 80/194] eta: 0:00:11 time: 0.0863 data_time: 0.0186 memory: 1818 2023/02/18 03:09:07 - mmengine - INFO - Epoch(val) [40][100/194] eta: 0:00:09 time: 0.0915 data_time: 0.0228 memory: 1818 2023/02/18 03:09:09 - mmengine - INFO - Epoch(val) [40][120/194] eta: 0:00:06 time: 0.0856 data_time: 0.0168 memory: 1818 2023/02/18 03:09:11 - mmengine - INFO - Epoch(val) [40][140/194] eta: 0:00:05 time: 0.0896 data_time: 0.0207 memory: 1818 2023/02/18 03:09:12 - mmengine - INFO - Epoch(val) [40][160/194] eta: 0:00:03 time: 0.0811 data_time: 0.0131 memory: 1818 2023/02/18 03:09:14 - mmengine - INFO - Epoch(val) [40][180/194] eta: 0:00:01 time: 0.0889 data_time: 0.0183 memory: 1818 2023/02/18 03:09:16 - mmengine - INFO - Epoch(val) [40][194/194] acc/top1: 0.5887 acc/top5: 0.8533 acc/mean1: 0.5206 2023/02/18 03:09:22 - mmengine - INFO - Epoch(train) [41][ 20/1320] lr: 2.0000e-03 eta: 0:56:43 time: 0.3016 data_time: 0.0419 memory: 13708 grad_norm: 6.5243 loss: 1.0382 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0382 2023/02/18 03:09:27 - mmengine - INFO - Epoch(train) [41][ 40/1320] lr: 2.0000e-03 eta: 0:56:38 time: 0.2579 data_time: 0.0112 memory: 13708 grad_norm: 6.4902 loss: 1.0526 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0526 2023/02/18 03:09:33 - mmengine - INFO - Epoch(train) [41][ 60/1320] lr: 2.0000e-03 eta: 0:56:32 time: 0.2553 data_time: 0.0106 memory: 13708 grad_norm: 6.4095 loss: 1.2081 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2081 2023/02/18 03:09:38 - mmengine - INFO - Epoch(train) [41][ 80/1320] lr: 2.0000e-03 eta: 0:56:27 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 6.1306 loss: 0.9466 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9466 2023/02/18 03:09:43 - mmengine - INFO - Epoch(train) [41][ 100/1320] lr: 2.0000e-03 eta: 0:56:22 time: 0.2567 data_time: 0.0111 memory: 13708 grad_norm: 6.4438 loss: 1.1550 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1550 2023/02/18 03:09:48 - mmengine - INFO - Epoch(train) [41][ 120/1320] lr: 2.0000e-03 eta: 0:56:17 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 6.4817 loss: 1.2088 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2088 2023/02/18 03:09:53 - mmengine - INFO - Epoch(train) [41][ 140/1320] lr: 2.0000e-03 eta: 0:56:12 time: 0.2586 data_time: 0.0138 memory: 13708 grad_norm: 6.5276 loss: 1.1292 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.1292 2023/02/18 03:09:58 - mmengine - INFO - Epoch(train) [41][ 160/1320] lr: 2.0000e-03 eta: 0:56:07 time: 0.2568 data_time: 0.0105 memory: 13708 grad_norm: 6.4715 loss: 1.0676 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0676 2023/02/18 03:10:03 - mmengine - INFO - Epoch(train) [41][ 180/1320] lr: 2.0000e-03 eta: 0:56:01 time: 0.2560 data_time: 0.0113 memory: 13708 grad_norm: 6.3936 loss: 1.0325 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0325 2023/02/18 03:10:08 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:10:08 - mmengine - INFO - Epoch(train) [41][ 200/1320] lr: 2.0000e-03 eta: 0:55:56 time: 0.2560 data_time: 0.0111 memory: 13708 grad_norm: 6.6314 loss: 1.1248 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1248 2023/02/18 03:10:14 - mmengine - INFO - Epoch(train) [41][ 220/1320] lr: 2.0000e-03 eta: 0:55:51 time: 0.2559 data_time: 0.0105 memory: 13708 grad_norm: 6.6125 loss: 1.1195 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1195 2023/02/18 03:10:19 - mmengine - INFO - Epoch(train) [41][ 240/1320] lr: 2.0000e-03 eta: 0:55:46 time: 0.2562 data_time: 0.0114 memory: 13708 grad_norm: 6.6650 loss: 1.0694 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.0694 2023/02/18 03:10:24 - mmengine - INFO - Epoch(train) [41][ 260/1320] lr: 2.0000e-03 eta: 0:55:41 time: 0.2572 data_time: 0.0119 memory: 13708 grad_norm: 6.5414 loss: 0.9444 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9444 2023/02/18 03:10:29 - mmengine - INFO - Epoch(train) [41][ 280/1320] lr: 2.0000e-03 eta: 0:55:36 time: 0.2578 data_time: 0.0126 memory: 13708 grad_norm: 6.5397 loss: 1.0061 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0061 2023/02/18 03:10:34 - mmengine - INFO - Epoch(train) [41][ 300/1320] lr: 2.0000e-03 eta: 0:55:30 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 6.4414 loss: 0.9974 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9974 2023/02/18 03:10:39 - mmengine - INFO - Epoch(train) [41][ 320/1320] lr: 2.0000e-03 eta: 0:55:25 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 6.7182 loss: 1.1262 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1262 2023/02/18 03:10:44 - mmengine - INFO - Epoch(train) [41][ 340/1320] lr: 2.0000e-03 eta: 0:55:20 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 6.5135 loss: 1.0147 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0147 2023/02/18 03:10:50 - mmengine - INFO - Epoch(train) [41][ 360/1320] lr: 2.0000e-03 eta: 0:55:15 time: 0.2560 data_time: 0.0106 memory: 13708 grad_norm: 6.4580 loss: 1.1694 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1694 2023/02/18 03:10:55 - mmengine - INFO - Epoch(train) [41][ 380/1320] lr: 2.0000e-03 eta: 0:55:10 time: 0.2559 data_time: 0.0106 memory: 13708 grad_norm: 6.6411 loss: 1.1698 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1698 2023/02/18 03:11:00 - mmengine - INFO - Epoch(train) [41][ 400/1320] lr: 2.0000e-03 eta: 0:55:04 time: 0.2565 data_time: 0.0112 memory: 13708 grad_norm: 6.3634 loss: 1.0182 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.0182 2023/02/18 03:11:05 - mmengine - INFO - Epoch(train) [41][ 420/1320] lr: 2.0000e-03 eta: 0:54:59 time: 0.2558 data_time: 0.0105 memory: 13708 grad_norm: 6.6463 loss: 1.1167 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1167 2023/02/18 03:11:10 - mmengine - INFO - Epoch(train) [41][ 440/1320] lr: 2.0000e-03 eta: 0:54:54 time: 0.2564 data_time: 0.0112 memory: 13708 grad_norm: 6.6489 loss: 1.0469 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.0469 2023/02/18 03:11:15 - mmengine - INFO - Epoch(train) [41][ 460/1320] lr: 2.0000e-03 eta: 0:54:49 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 6.5434 loss: 0.9795 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9795 2023/02/18 03:11:20 - mmengine - INFO - Epoch(train) [41][ 480/1320] lr: 2.0000e-03 eta: 0:54:44 time: 0.2562 data_time: 0.0106 memory: 13708 grad_norm: 6.5848 loss: 1.1705 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1705 2023/02/18 03:11:25 - mmengine - INFO - Epoch(train) [41][ 500/1320] lr: 2.0000e-03 eta: 0:54:39 time: 0.2567 data_time: 0.0109 memory: 13708 grad_norm: 6.7870 loss: 1.0372 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0372 2023/02/18 03:11:31 - mmengine - INFO - Epoch(train) [41][ 520/1320] lr: 2.0000e-03 eta: 0:54:33 time: 0.2567 data_time: 0.0112 memory: 13708 grad_norm: 6.5683 loss: 1.0777 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0777 2023/02/18 03:11:36 - mmengine - INFO - Epoch(train) [41][ 540/1320] lr: 2.0000e-03 eta: 0:54:28 time: 0.2568 data_time: 0.0109 memory: 13708 grad_norm: 6.5363 loss: 1.0833 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0833 2023/02/18 03:11:41 - mmengine - INFO - Epoch(train) [41][ 560/1320] lr: 2.0000e-03 eta: 0:54:23 time: 0.2568 data_time: 0.0109 memory: 13708 grad_norm: 6.5869 loss: 1.1777 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1777 2023/02/18 03:11:46 - mmengine - INFO - Epoch(train) [41][ 580/1320] lr: 2.0000e-03 eta: 0:54:18 time: 0.2568 data_time: 0.0116 memory: 13708 grad_norm: 6.5412 loss: 1.1585 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1585 2023/02/18 03:11:51 - mmengine - INFO - Epoch(train) [41][ 600/1320] lr: 2.0000e-03 eta: 0:54:13 time: 0.2558 data_time: 0.0106 memory: 13708 grad_norm: 6.4817 loss: 1.0327 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0327 2023/02/18 03:11:56 - mmengine - INFO - Epoch(train) [41][ 620/1320] lr: 2.0000e-03 eta: 0:54:08 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 6.6903 loss: 1.0154 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0154 2023/02/18 03:12:01 - mmengine - INFO - Epoch(train) [41][ 640/1320] lr: 2.0000e-03 eta: 0:54:02 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 6.5663 loss: 1.1451 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1451 2023/02/18 03:12:06 - mmengine - INFO - Epoch(train) [41][ 660/1320] lr: 2.0000e-03 eta: 0:53:57 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 6.7265 loss: 1.0616 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0616 2023/02/18 03:12:12 - mmengine - INFO - Epoch(train) [41][ 680/1320] lr: 2.0000e-03 eta: 0:53:52 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 6.5191 loss: 1.0676 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.0676 2023/02/18 03:12:17 - mmengine - INFO - Epoch(train) [41][ 700/1320] lr: 2.0000e-03 eta: 0:53:47 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 6.6989 loss: 1.0403 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0403 2023/02/18 03:12:22 - mmengine - INFO - Epoch(train) [41][ 720/1320] lr: 2.0000e-03 eta: 0:53:42 time: 0.2569 data_time: 0.0112 memory: 13708 grad_norm: 6.7149 loss: 1.1886 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1886 2023/02/18 03:12:27 - mmengine - INFO - Epoch(train) [41][ 740/1320] lr: 2.0000e-03 eta: 0:53:37 time: 0.2562 data_time: 0.0112 memory: 13708 grad_norm: 6.6724 loss: 1.1572 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1572 2023/02/18 03:12:32 - mmengine - INFO - Epoch(train) [41][ 760/1320] lr: 2.0000e-03 eta: 0:53:31 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 6.8817 loss: 1.0934 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0934 2023/02/18 03:12:37 - mmengine - INFO - Epoch(train) [41][ 780/1320] lr: 2.0000e-03 eta: 0:53:26 time: 0.2555 data_time: 0.0109 memory: 13708 grad_norm: 6.8893 loss: 0.9519 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9519 2023/02/18 03:12:42 - mmengine - INFO - Epoch(train) [41][ 800/1320] lr: 2.0000e-03 eta: 0:53:21 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 6.5433 loss: 1.1346 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1346 2023/02/18 03:12:47 - mmengine - INFO - Epoch(train) [41][ 820/1320] lr: 2.0000e-03 eta: 0:53:16 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 6.5843 loss: 1.1274 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1274 2023/02/18 03:12:53 - mmengine - INFO - Epoch(train) [41][ 840/1320] lr: 2.0000e-03 eta: 0:53:11 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 6.5524 loss: 1.0477 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0477 2023/02/18 03:12:58 - mmengine - INFO - Epoch(train) [41][ 860/1320] lr: 2.0000e-03 eta: 0:53:06 time: 0.2560 data_time: 0.0103 memory: 13708 grad_norm: 6.6672 loss: 1.2186 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2186 2023/02/18 03:13:03 - mmengine - INFO - Epoch(train) [41][ 880/1320] lr: 2.0000e-03 eta: 0:53:00 time: 0.2568 data_time: 0.0112 memory: 13708 grad_norm: 6.7080 loss: 0.9826 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9826 2023/02/18 03:13:08 - mmengine - INFO - Epoch(train) [41][ 900/1320] lr: 2.0000e-03 eta: 0:52:55 time: 0.2555 data_time: 0.0108 memory: 13708 grad_norm: 6.6983 loss: 1.1276 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1276 2023/02/18 03:13:13 - mmengine - INFO - Epoch(train) [41][ 920/1320] lr: 2.0000e-03 eta: 0:52:50 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 6.7958 loss: 1.1472 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1472 2023/02/18 03:13:18 - mmengine - INFO - Epoch(train) [41][ 940/1320] lr: 2.0000e-03 eta: 0:52:45 time: 0.2566 data_time: 0.0108 memory: 13708 grad_norm: 6.5355 loss: 1.1233 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1233 2023/02/18 03:13:23 - mmengine - INFO - Epoch(train) [41][ 960/1320] lr: 2.0000e-03 eta: 0:52:40 time: 0.2569 data_time: 0.0115 memory: 13708 grad_norm: 6.8283 loss: 1.0714 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0714 2023/02/18 03:13:29 - mmengine - INFO - Epoch(train) [41][ 980/1320] lr: 2.0000e-03 eta: 0:52:34 time: 0.2582 data_time: 0.0130 memory: 13708 grad_norm: 6.7671 loss: 1.2085 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2085 2023/02/18 03:13:34 - mmengine - INFO - Epoch(train) [41][1000/1320] lr: 2.0000e-03 eta: 0:52:29 time: 0.2565 data_time: 0.0110 memory: 13708 grad_norm: 6.7951 loss: 1.1608 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.1608 2023/02/18 03:13:39 - mmengine - INFO - Epoch(train) [41][1020/1320] lr: 2.0000e-03 eta: 0:52:24 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 6.7947 loss: 0.9664 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9664 2023/02/18 03:13:44 - mmengine - INFO - Epoch(train) [41][1040/1320] lr: 2.0000e-03 eta: 0:52:19 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 6.7600 loss: 1.0303 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0303 2023/02/18 03:13:49 - mmengine - INFO - Epoch(train) [41][1060/1320] lr: 2.0000e-03 eta: 0:52:14 time: 0.2575 data_time: 0.0124 memory: 13708 grad_norm: 6.8844 loss: 1.1307 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1307 2023/02/18 03:13:54 - mmengine - INFO - Epoch(train) [41][1080/1320] lr: 2.0000e-03 eta: 0:52:09 time: 0.2563 data_time: 0.0112 memory: 13708 grad_norm: 6.9058 loss: 1.1267 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1267 2023/02/18 03:13:59 - mmengine - INFO - Epoch(train) [41][1100/1320] lr: 2.0000e-03 eta: 0:52:03 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 6.7572 loss: 1.2271 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2271 2023/02/18 03:14:04 - mmengine - INFO - Epoch(train) [41][1120/1320] lr: 2.0000e-03 eta: 0:51:58 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 6.8983 loss: 1.0025 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0025 2023/02/18 03:14:10 - mmengine - INFO - Epoch(train) [41][1140/1320] lr: 2.0000e-03 eta: 0:51:53 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 6.5807 loss: 1.0954 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0954 2023/02/18 03:14:15 - mmengine - INFO - Epoch(train) [41][1160/1320] lr: 2.0000e-03 eta: 0:51:48 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 6.6084 loss: 0.9504 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9504 2023/02/18 03:14:20 - mmengine - INFO - Epoch(train) [41][1180/1320] lr: 2.0000e-03 eta: 0:51:43 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 6.5856 loss: 1.0227 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0227 2023/02/18 03:14:25 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:14:25 - mmengine - INFO - Epoch(train) [41][1200/1320] lr: 2.0000e-03 eta: 0:51:38 time: 0.2564 data_time: 0.0110 memory: 13708 grad_norm: 6.8456 loss: 1.0744 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.0744 2023/02/18 03:14:30 - mmengine - INFO - Epoch(train) [41][1220/1320] lr: 2.0000e-03 eta: 0:51:32 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 6.6994 loss: 1.1092 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1092 2023/02/18 03:14:35 - mmengine - INFO - Epoch(train) [41][1240/1320] lr: 2.0000e-03 eta: 0:51:27 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 6.8350 loss: 1.0860 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0860 2023/02/18 03:14:40 - mmengine - INFO - Epoch(train) [41][1260/1320] lr: 2.0000e-03 eta: 0:51:22 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 6.7702 loss: 1.0005 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0005 2023/02/18 03:14:45 - mmengine - INFO - Epoch(train) [41][1280/1320] lr: 2.0000e-03 eta: 0:51:17 time: 0.2551 data_time: 0.0104 memory: 13708 grad_norm: 6.9394 loss: 1.1582 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1582 2023/02/18 03:14:51 - mmengine - INFO - Epoch(train) [41][1300/1320] lr: 2.0000e-03 eta: 0:51:12 time: 0.2562 data_time: 0.0114 memory: 13708 grad_norm: 6.8159 loss: 0.9582 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9582 2023/02/18 03:14:56 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:14:56 - mmengine - INFO - Epoch(train) [41][1320/1320] lr: 2.0000e-03 eta: 0:51:07 time: 0.2517 data_time: 0.0110 memory: 13708 grad_norm: 6.6087 loss: 1.0758 top1_acc: 0.9091 top5_acc: 1.0000 loss_cls: 1.0758 2023/02/18 03:14:58 - mmengine - INFO - Epoch(val) [41][ 20/194] eta: 0:00:23 time: 0.1359 data_time: 0.0669 memory: 1818 2023/02/18 03:15:00 - mmengine - INFO - Epoch(val) [41][ 40/194] eta: 0:00:17 time: 0.0871 data_time: 0.0188 memory: 1818 2023/02/18 03:15:02 - mmengine - INFO - Epoch(val) [41][ 60/194] eta: 0:00:13 time: 0.0891 data_time: 0.0204 memory: 1818 2023/02/18 03:15:04 - mmengine - INFO - Epoch(val) [41][ 80/194] eta: 0:00:11 time: 0.0933 data_time: 0.0252 memory: 1818 2023/02/18 03:15:06 - mmengine - INFO - Epoch(val) [41][100/194] eta: 0:00:09 time: 0.0889 data_time: 0.0207 memory: 1818 2023/02/18 03:15:07 - mmengine - INFO - Epoch(val) [41][120/194] eta: 0:00:07 time: 0.0841 data_time: 0.0160 memory: 1818 2023/02/18 03:15:09 - mmengine - INFO - Epoch(val) [41][140/194] eta: 0:00:05 time: 0.0929 data_time: 0.0234 memory: 1818 2023/02/18 03:15:11 - mmengine - INFO - Epoch(val) [41][160/194] eta: 0:00:03 time: 0.0812 data_time: 0.0127 memory: 1818 2023/02/18 03:15:12 - mmengine - INFO - Epoch(val) [41][180/194] eta: 0:00:01 time: 0.0861 data_time: 0.0171 memory: 1818 2023/02/18 03:15:14 - mmengine - INFO - Epoch(val) [41][194/194] acc/top1: 0.5863 acc/top5: 0.8502 acc/mean1: 0.5246 2023/02/18 03:15:20 - mmengine - INFO - Epoch(train) [42][ 20/1320] lr: 2.0000e-03 eta: 0:51:02 time: 0.3021 data_time: 0.0447 memory: 13708 grad_norm: 6.6129 loss: 1.0287 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0287 2023/02/18 03:15:25 - mmengine - INFO - Epoch(train) [42][ 40/1320] lr: 2.0000e-03 eta: 0:50:56 time: 0.2573 data_time: 0.0113 memory: 13708 grad_norm: 6.6970 loss: 1.0984 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0984 2023/02/18 03:15:31 - mmengine - INFO - Epoch(train) [42][ 60/1320] lr: 2.0000e-03 eta: 0:50:51 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 6.8077 loss: 1.0375 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0375 2023/02/18 03:15:36 - mmengine - INFO - Epoch(train) [42][ 80/1320] lr: 2.0000e-03 eta: 0:50:46 time: 0.2579 data_time: 0.0117 memory: 13708 grad_norm: 6.7966 loss: 0.8955 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8955 2023/02/18 03:15:41 - mmengine - INFO - Epoch(train) [42][ 100/1320] lr: 2.0000e-03 eta: 0:50:41 time: 0.2566 data_time: 0.0105 memory: 13708 grad_norm: 6.8314 loss: 1.0690 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0690 2023/02/18 03:15:46 - mmengine - INFO - Epoch(train) [42][ 120/1320] lr: 2.0000e-03 eta: 0:50:36 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 6.8196 loss: 1.0601 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0601 2023/02/18 03:15:51 - mmengine - INFO - Epoch(train) [42][ 140/1320] lr: 2.0000e-03 eta: 0:50:31 time: 0.2559 data_time: 0.0104 memory: 13708 grad_norm: 6.9318 loss: 1.2274 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2274 2023/02/18 03:15:56 - mmengine - INFO - Epoch(train) [42][ 160/1320] lr: 2.0000e-03 eta: 0:50:25 time: 0.2562 data_time: 0.0106 memory: 13708 grad_norm: 6.6419 loss: 1.0629 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0629 2023/02/18 03:16:01 - mmengine - INFO - Epoch(train) [42][ 180/1320] lr: 2.0000e-03 eta: 0:50:20 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 6.6541 loss: 1.1407 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1407 2023/02/18 03:16:06 - mmengine - INFO - Epoch(train) [42][ 200/1320] lr: 2.0000e-03 eta: 0:50:15 time: 0.2557 data_time: 0.0104 memory: 13708 grad_norm: 6.5749 loss: 1.2760 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2760 2023/02/18 03:16:12 - mmengine - INFO - Epoch(train) [42][ 220/1320] lr: 2.0000e-03 eta: 0:50:10 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 6.7333 loss: 1.1171 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1171 2023/02/18 03:16:17 - mmengine - INFO - Epoch(train) [42][ 240/1320] lr: 2.0000e-03 eta: 0:50:05 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 6.5304 loss: 1.1380 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1380 2023/02/18 03:16:22 - mmengine - INFO - Epoch(train) [42][ 260/1320] lr: 2.0000e-03 eta: 0:50:00 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 6.6376 loss: 1.0815 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0815 2023/02/18 03:16:27 - mmengine - INFO - Epoch(train) [42][ 280/1320] lr: 2.0000e-03 eta: 0:49:54 time: 0.2562 data_time: 0.0112 memory: 13708 grad_norm: 6.7478 loss: 1.0931 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0931 2023/02/18 03:16:32 - mmengine - INFO - Epoch(train) [42][ 300/1320] lr: 2.0000e-03 eta: 0:49:49 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 6.6245 loss: 1.2650 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2650 2023/02/18 03:16:37 - mmengine - INFO - Epoch(train) [42][ 320/1320] lr: 2.0000e-03 eta: 0:49:44 time: 0.2564 data_time: 0.0119 memory: 13708 grad_norm: 6.6778 loss: 1.0643 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0643 2023/02/18 03:16:42 - mmengine - INFO - Epoch(train) [42][ 340/1320] lr: 2.0000e-03 eta: 0:49:39 time: 0.2557 data_time: 0.0103 memory: 13708 grad_norm: 6.8421 loss: 1.0168 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0168 2023/02/18 03:16:47 - mmengine - INFO - Epoch(train) [42][ 360/1320] lr: 2.0000e-03 eta: 0:49:34 time: 0.2567 data_time: 0.0111 memory: 13708 grad_norm: 6.7798 loss: 1.1143 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1143 2023/02/18 03:16:53 - mmengine - INFO - Epoch(train) [42][ 380/1320] lr: 2.0000e-03 eta: 0:49:28 time: 0.2567 data_time: 0.0106 memory: 13708 grad_norm: 6.7212 loss: 1.0613 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0613 2023/02/18 03:16:58 - mmengine - INFO - Epoch(train) [42][ 400/1320] lr: 2.0000e-03 eta: 0:49:23 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 6.6991 loss: 1.2590 top1_acc: 0.7500 top5_acc: 0.7500 loss_cls: 1.2590 2023/02/18 03:17:03 - mmengine - INFO - Epoch(train) [42][ 420/1320] lr: 2.0000e-03 eta: 0:49:18 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 6.7937 loss: 1.0946 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0946 2023/02/18 03:17:08 - mmengine - INFO - Epoch(train) [42][ 440/1320] lr: 2.0000e-03 eta: 0:49:13 time: 0.2558 data_time: 0.0114 memory: 13708 grad_norm: 6.8589 loss: 0.9637 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9637 2023/02/18 03:17:13 - mmengine - INFO - Epoch(train) [42][ 460/1320] lr: 2.0000e-03 eta: 0:49:08 time: 0.2565 data_time: 0.0112 memory: 13708 grad_norm: 6.5034 loss: 1.1335 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1335 2023/02/18 03:17:18 - mmengine - INFO - Epoch(train) [42][ 480/1320] lr: 2.0000e-03 eta: 0:49:03 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 6.5722 loss: 1.0369 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0369 2023/02/18 03:17:23 - mmengine - INFO - Epoch(train) [42][ 500/1320] lr: 2.0000e-03 eta: 0:48:57 time: 0.2575 data_time: 0.0121 memory: 13708 grad_norm: 6.6294 loss: 1.0116 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.0116 2023/02/18 03:17:29 - mmengine - INFO - Epoch(train) [42][ 520/1320] lr: 2.0000e-03 eta: 0:48:52 time: 0.2563 data_time: 0.0114 memory: 13708 grad_norm: 6.8556 loss: 1.1360 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.1360 2023/02/18 03:17:34 - mmengine - INFO - Epoch(train) [42][ 540/1320] lr: 2.0000e-03 eta: 0:48:47 time: 0.2575 data_time: 0.0118 memory: 13708 grad_norm: 6.8296 loss: 1.1141 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1141 2023/02/18 03:17:39 - mmengine - INFO - Epoch(train) [42][ 560/1320] lr: 2.0000e-03 eta: 0:48:42 time: 0.2566 data_time: 0.0114 memory: 13708 grad_norm: 7.0158 loss: 1.2787 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.2787 2023/02/18 03:17:44 - mmengine - INFO - Epoch(train) [42][ 580/1320] lr: 2.0000e-03 eta: 0:48:37 time: 0.2564 data_time: 0.0106 memory: 13708 grad_norm: 6.9310 loss: 0.9564 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9564 2023/02/18 03:17:49 - mmengine - INFO - Epoch(train) [42][ 600/1320] lr: 2.0000e-03 eta: 0:48:32 time: 0.2568 data_time: 0.0121 memory: 13708 grad_norm: 6.7985 loss: 1.0069 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0069 2023/02/18 03:17:54 - mmengine - INFO - Epoch(train) [42][ 620/1320] lr: 2.0000e-03 eta: 0:48:26 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 6.9491 loss: 1.2180 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2180 2023/02/18 03:17:59 - mmengine - INFO - Epoch(train) [42][ 640/1320] lr: 2.0000e-03 eta: 0:48:21 time: 0.2573 data_time: 0.0108 memory: 13708 grad_norm: 6.6673 loss: 1.1007 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1007 2023/02/18 03:18:04 - mmengine - INFO - Epoch(train) [42][ 660/1320] lr: 2.0000e-03 eta: 0:48:16 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 6.7576 loss: 1.0128 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0128 2023/02/18 03:18:10 - mmengine - INFO - Epoch(train) [42][ 680/1320] lr: 2.0000e-03 eta: 0:48:11 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 6.5476 loss: 0.9905 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9905 2023/02/18 03:18:15 - mmengine - INFO - Epoch(train) [42][ 700/1320] lr: 2.0000e-03 eta: 0:48:06 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 6.8462 loss: 1.1330 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1330 2023/02/18 03:18:20 - mmengine - INFO - Epoch(train) [42][ 720/1320] lr: 2.0000e-03 eta: 0:48:01 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 6.7477 loss: 1.2721 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2721 2023/02/18 03:18:25 - mmengine - INFO - Epoch(train) [42][ 740/1320] lr: 2.0000e-03 eta: 0:47:55 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 6.9910 loss: 1.0960 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0960 2023/02/18 03:18:30 - mmengine - INFO - Epoch(train) [42][ 760/1320] lr: 2.0000e-03 eta: 0:47:50 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 6.7917 loss: 1.0567 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0567 2023/02/18 03:18:35 - mmengine - INFO - Epoch(train) [42][ 780/1320] lr: 2.0000e-03 eta: 0:47:45 time: 0.2563 data_time: 0.0113 memory: 13708 grad_norm: 6.8361 loss: 1.0078 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0078 2023/02/18 03:18:40 - mmengine - INFO - Epoch(train) [42][ 800/1320] lr: 2.0000e-03 eta: 0:47:40 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 6.9446 loss: 1.3614 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.3614 2023/02/18 03:18:45 - mmengine - INFO - Epoch(train) [42][ 820/1320] lr: 2.0000e-03 eta: 0:47:35 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 6.8193 loss: 1.0908 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0908 2023/02/18 03:18:51 - mmengine - INFO - Epoch(train) [42][ 840/1320] lr: 2.0000e-03 eta: 0:47:30 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 6.8495 loss: 1.1377 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.1377 2023/02/18 03:18:56 - mmengine - INFO - Epoch(train) [42][ 860/1320] lr: 2.0000e-03 eta: 0:47:24 time: 0.2577 data_time: 0.0126 memory: 13708 grad_norm: 6.5311 loss: 1.0464 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0464 2023/02/18 03:19:01 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:19:01 - mmengine - INFO - Epoch(train) [42][ 880/1320] lr: 2.0000e-03 eta: 0:47:19 time: 0.2568 data_time: 0.0110 memory: 13708 grad_norm: 6.6693 loss: 1.0761 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.0761 2023/02/18 03:19:06 - mmengine - INFO - Epoch(train) [42][ 900/1320] lr: 2.0000e-03 eta: 0:47:14 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 6.9072 loss: 1.2286 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2286 2023/02/18 03:19:11 - mmengine - INFO - Epoch(train) [42][ 920/1320] lr: 2.0000e-03 eta: 0:47:09 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 6.9203 loss: 0.9895 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9895 2023/02/18 03:19:16 - mmengine - INFO - Epoch(train) [42][ 940/1320] lr: 2.0000e-03 eta: 0:47:04 time: 0.2567 data_time: 0.0111 memory: 13708 grad_norm: 6.5921 loss: 1.0218 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.0218 2023/02/18 03:19:21 - mmengine - INFO - Epoch(train) [42][ 960/1320] lr: 2.0000e-03 eta: 0:46:59 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 6.8739 loss: 1.2026 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.2026 2023/02/18 03:19:27 - mmengine - INFO - Epoch(train) [42][ 980/1320] lr: 2.0000e-03 eta: 0:46:53 time: 0.2554 data_time: 0.0104 memory: 13708 grad_norm: 6.8899 loss: 1.0577 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.0577 2023/02/18 03:19:32 - mmengine - INFO - Epoch(train) [42][1000/1320] lr: 2.0000e-03 eta: 0:46:48 time: 0.2564 data_time: 0.0113 memory: 13708 grad_norm: 6.8122 loss: 0.9050 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9050 2023/02/18 03:19:37 - mmengine - INFO - Epoch(train) [42][1020/1320] lr: 2.0000e-03 eta: 0:46:43 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 6.8572 loss: 1.0523 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0523 2023/02/18 03:19:42 - mmengine - INFO - Epoch(train) [42][1040/1320] lr: 2.0000e-03 eta: 0:46:38 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 6.8552 loss: 0.9145 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9145 2023/02/18 03:19:47 - mmengine - INFO - Epoch(train) [42][1060/1320] lr: 2.0000e-03 eta: 0:46:33 time: 0.2572 data_time: 0.0110 memory: 13708 grad_norm: 6.8323 loss: 1.0638 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0638 2023/02/18 03:19:52 - mmengine - INFO - Epoch(train) [42][1080/1320] lr: 2.0000e-03 eta: 0:46:28 time: 0.2556 data_time: 0.0112 memory: 13708 grad_norm: 6.8684 loss: 1.1943 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1943 2023/02/18 03:19:57 - mmengine - INFO - Epoch(train) [42][1100/1320] lr: 2.0000e-03 eta: 0:46:22 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 7.0125 loss: 0.9978 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9978 2023/02/18 03:20:02 - mmengine - INFO - Epoch(train) [42][1120/1320] lr: 2.0000e-03 eta: 0:46:17 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 6.7634 loss: 0.9659 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9659 2023/02/18 03:20:08 - mmengine - INFO - Epoch(train) [42][1140/1320] lr: 2.0000e-03 eta: 0:46:12 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 6.8000 loss: 1.1294 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1294 2023/02/18 03:20:13 - mmengine - INFO - Epoch(train) [42][1160/1320] lr: 2.0000e-03 eta: 0:46:07 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 6.7085 loss: 1.1469 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1469 2023/02/18 03:20:18 - mmengine - INFO - Epoch(train) [42][1180/1320] lr: 2.0000e-03 eta: 0:46:02 time: 0.2561 data_time: 0.0105 memory: 13708 grad_norm: 7.0203 loss: 1.0742 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0742 2023/02/18 03:20:23 - mmengine - INFO - Epoch(train) [42][1200/1320] lr: 2.0000e-03 eta: 0:45:56 time: 0.2558 data_time: 0.0110 memory: 13708 grad_norm: 6.9976 loss: 1.1110 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1110 2023/02/18 03:20:28 - mmengine - INFO - Epoch(train) [42][1220/1320] lr: 2.0000e-03 eta: 0:45:51 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 6.5924 loss: 1.1170 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1170 2023/02/18 03:20:33 - mmengine - INFO - Epoch(train) [42][1240/1320] lr: 2.0000e-03 eta: 0:45:46 time: 0.2567 data_time: 0.0110 memory: 13708 grad_norm: 6.7544 loss: 1.0444 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 1.0444 2023/02/18 03:20:38 - mmengine - INFO - Epoch(train) [42][1260/1320] lr: 2.0000e-03 eta: 0:45:41 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 6.8316 loss: 1.0129 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0129 2023/02/18 03:20:43 - mmengine - INFO - Epoch(train) [42][1280/1320] lr: 2.0000e-03 eta: 0:45:36 time: 0.2568 data_time: 0.0111 memory: 13708 grad_norm: 6.9007 loss: 1.1826 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1826 2023/02/18 03:20:49 - mmengine - INFO - Epoch(train) [42][1300/1320] lr: 2.0000e-03 eta: 0:45:31 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 6.8951 loss: 1.0000 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0000 2023/02/18 03:20:54 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:20:54 - mmengine - INFO - Epoch(train) [42][1320/1320] lr: 2.0000e-03 eta: 0:45:25 time: 0.2516 data_time: 0.0105 memory: 13708 grad_norm: 7.1511 loss: 0.9843 top1_acc: 0.9091 top5_acc: 1.0000 loss_cls: 0.9843 2023/02/18 03:20:54 - mmengine - INFO - Saving checkpoint at 42 epochs 2023/02/18 03:20:57 - mmengine - INFO - Epoch(val) [42][ 20/194] eta: 0:00:22 time: 0.1310 data_time: 0.0619 memory: 1818 2023/02/18 03:20:59 - mmengine - INFO - Epoch(val) [42][ 40/194] eta: 0:00:16 time: 0.0869 data_time: 0.0170 memory: 1818 2023/02/18 03:21:01 - mmengine - INFO - Epoch(val) [42][ 60/194] eta: 0:00:13 time: 0.0885 data_time: 0.0205 memory: 1818 2023/02/18 03:21:03 - mmengine - INFO - Epoch(val) [42][ 80/194] eta: 0:00:11 time: 0.0857 data_time: 0.0174 memory: 1818 2023/02/18 03:21:04 - mmengine - INFO - Epoch(val) [42][100/194] eta: 0:00:09 time: 0.0869 data_time: 0.0185 memory: 1818 2023/02/18 03:21:06 - mmengine - INFO - Epoch(val) [42][120/194] eta: 0:00:06 time: 0.0859 data_time: 0.0168 memory: 1818 2023/02/18 03:21:08 - mmengine - INFO - Epoch(val) [42][140/194] eta: 0:00:05 time: 0.0913 data_time: 0.0232 memory: 1818 2023/02/18 03:21:10 - mmengine - INFO - Epoch(val) [42][160/194] eta: 0:00:03 time: 0.0805 data_time: 0.0118 memory: 1818 2023/02/18 03:21:11 - mmengine - INFO - Epoch(val) [42][180/194] eta: 0:00:01 time: 0.0832 data_time: 0.0166 memory: 1818 2023/02/18 03:21:13 - mmengine - INFO - Epoch(val) [42][194/194] acc/top1: 0.5800 acc/top5: 0.8464 acc/mean1: 0.5222 2023/02/18 03:21:19 - mmengine - INFO - Epoch(train) [43][ 20/1320] lr: 2.0000e-03 eta: 0:45:20 time: 0.3006 data_time: 0.0452 memory: 13708 grad_norm: 6.8859 loss: 0.9764 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9764 2023/02/18 03:21:24 - mmengine - INFO - Epoch(train) [43][ 40/1320] lr: 2.0000e-03 eta: 0:45:15 time: 0.2572 data_time: 0.0111 memory: 13708 grad_norm: 6.9452 loss: 0.9293 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.9293 2023/02/18 03:21:29 - mmengine - INFO - Epoch(train) [43][ 60/1320] lr: 2.0000e-03 eta: 0:45:10 time: 0.2567 data_time: 0.0107 memory: 13708 grad_norm: 6.8264 loss: 1.1606 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1606 2023/02/18 03:21:34 - mmengine - INFO - Epoch(train) [43][ 80/1320] lr: 2.0000e-03 eta: 0:45:05 time: 0.2555 data_time: 0.0100 memory: 13708 grad_norm: 6.8669 loss: 1.0699 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0699 2023/02/18 03:21:40 - mmengine - INFO - Epoch(train) [43][ 100/1320] lr: 2.0000e-03 eta: 0:45:00 time: 0.2558 data_time: 0.0103 memory: 13708 grad_norm: 6.5235 loss: 1.0236 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0236 2023/02/18 03:21:45 - mmengine - INFO - Epoch(train) [43][ 120/1320] lr: 2.0000e-03 eta: 0:44:55 time: 0.2575 data_time: 0.0108 memory: 13708 grad_norm: 6.8094 loss: 0.9154 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9154 2023/02/18 03:21:50 - mmengine - INFO - Epoch(train) [43][ 140/1320] lr: 2.0000e-03 eta: 0:44:49 time: 0.2558 data_time: 0.0104 memory: 13708 grad_norm: 6.8246 loss: 1.0923 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0923 2023/02/18 03:21:55 - mmengine - INFO - Epoch(train) [43][ 160/1320] lr: 2.0000e-03 eta: 0:44:44 time: 0.2570 data_time: 0.0110 memory: 13708 grad_norm: 6.8511 loss: 0.9990 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9990 2023/02/18 03:22:00 - mmengine - INFO - Epoch(train) [43][ 180/1320] lr: 2.0000e-03 eta: 0:44:39 time: 0.2566 data_time: 0.0110 memory: 13708 grad_norm: 6.7857 loss: 0.9659 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9659 2023/02/18 03:22:05 - mmengine - INFO - Epoch(train) [43][ 200/1320] lr: 2.0000e-03 eta: 0:44:34 time: 0.2566 data_time: 0.0117 memory: 13708 grad_norm: 6.8977 loss: 1.2261 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.2261 2023/02/18 03:22:10 - mmengine - INFO - Epoch(train) [43][ 220/1320] lr: 2.0000e-03 eta: 0:44:29 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 6.6770 loss: 1.0828 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.0828 2023/02/18 03:22:15 - mmengine - INFO - Epoch(train) [43][ 240/1320] lr: 2.0000e-03 eta: 0:44:24 time: 0.2559 data_time: 0.0102 memory: 13708 grad_norm: 6.7561 loss: 1.0092 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0092 2023/02/18 03:22:21 - mmengine - INFO - Epoch(train) [43][ 260/1320] lr: 2.0000e-03 eta: 0:44:18 time: 0.2564 data_time: 0.0114 memory: 13708 grad_norm: 6.7972 loss: 1.0557 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.0557 2023/02/18 03:22:26 - mmengine - INFO - Epoch(train) [43][ 280/1320] lr: 2.0000e-03 eta: 0:44:13 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 6.7240 loss: 1.1296 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1296 2023/02/18 03:22:31 - mmengine - INFO - Epoch(train) [43][ 300/1320] lr: 2.0000e-03 eta: 0:44:08 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 6.8644 loss: 1.0635 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0635 2023/02/18 03:22:36 - mmengine - INFO - Epoch(train) [43][ 320/1320] lr: 2.0000e-03 eta: 0:44:03 time: 0.2575 data_time: 0.0119 memory: 13708 grad_norm: 6.9658 loss: 1.1460 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1460 2023/02/18 03:22:41 - mmengine - INFO - Epoch(train) [43][ 340/1320] lr: 2.0000e-03 eta: 0:43:58 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 6.9029 loss: 1.1449 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1449 2023/02/18 03:22:46 - mmengine - INFO - Epoch(train) [43][ 360/1320] lr: 2.0000e-03 eta: 0:43:53 time: 0.2564 data_time: 0.0112 memory: 13708 grad_norm: 6.9764 loss: 0.9622 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9622 2023/02/18 03:22:51 - mmengine - INFO - Epoch(train) [43][ 380/1320] lr: 2.0000e-03 eta: 0:43:47 time: 0.2564 data_time: 0.0105 memory: 13708 grad_norm: 6.9745 loss: 1.2261 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2261 2023/02/18 03:22:57 - mmengine - INFO - Epoch(train) [43][ 400/1320] lr: 2.0000e-03 eta: 0:43:42 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 7.0301 loss: 1.0382 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0382 2023/02/18 03:23:02 - mmengine - INFO - Epoch(train) [43][ 420/1320] lr: 2.0000e-03 eta: 0:43:37 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 6.7423 loss: 0.9131 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9131 2023/02/18 03:23:07 - mmengine - INFO - Epoch(train) [43][ 440/1320] lr: 2.0000e-03 eta: 0:43:32 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 6.8532 loss: 1.1149 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1149 2023/02/18 03:23:12 - mmengine - INFO - Epoch(train) [43][ 460/1320] lr: 2.0000e-03 eta: 0:43:27 time: 0.2560 data_time: 0.0106 memory: 13708 grad_norm: 7.0365 loss: 1.0844 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0844 2023/02/18 03:23:17 - mmengine - INFO - Epoch(train) [43][ 480/1320] lr: 2.0000e-03 eta: 0:43:22 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 7.0527 loss: 1.0268 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0268 2023/02/18 03:23:22 - mmengine - INFO - Epoch(train) [43][ 500/1320] lr: 2.0000e-03 eta: 0:43:16 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 7.0604 loss: 1.0880 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0880 2023/02/18 03:23:27 - mmengine - INFO - Epoch(train) [43][ 520/1320] lr: 2.0000e-03 eta: 0:43:11 time: 0.2560 data_time: 0.0105 memory: 13708 grad_norm: 6.8848 loss: 1.0906 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.0906 2023/02/18 03:23:32 - mmengine - INFO - Epoch(train) [43][ 540/1320] lr: 2.0000e-03 eta: 0:43:06 time: 0.2574 data_time: 0.0123 memory: 13708 grad_norm: 6.9954 loss: 1.1551 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1551 2023/02/18 03:23:38 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:23:38 - mmengine - INFO - Epoch(train) [43][ 560/1320] lr: 2.0000e-03 eta: 0:43:01 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 7.0037 loss: 1.1834 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1834 2023/02/18 03:23:43 - mmengine - INFO - Epoch(train) [43][ 580/1320] lr: 2.0000e-03 eta: 0:42:56 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 7.0000 loss: 1.0319 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.0319 2023/02/18 03:23:48 - mmengine - INFO - Epoch(train) [43][ 600/1320] lr: 2.0000e-03 eta: 0:42:51 time: 0.2568 data_time: 0.0112 memory: 13708 grad_norm: 6.7534 loss: 1.0750 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0750 2023/02/18 03:23:53 - mmengine - INFO - Epoch(train) [43][ 620/1320] lr: 2.0000e-03 eta: 0:42:45 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 6.8322 loss: 0.9753 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9753 2023/02/18 03:23:58 - mmengine - INFO - Epoch(train) [43][ 640/1320] lr: 2.0000e-03 eta: 0:42:40 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 6.9577 loss: 0.9737 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9737 2023/02/18 03:24:03 - mmengine - INFO - Epoch(train) [43][ 660/1320] lr: 2.0000e-03 eta: 0:42:35 time: 0.2580 data_time: 0.0128 memory: 13708 grad_norm: 7.3049 loss: 0.9204 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9204 2023/02/18 03:24:08 - mmengine - INFO - Epoch(train) [43][ 680/1320] lr: 2.0000e-03 eta: 0:42:30 time: 0.2577 data_time: 0.0123 memory: 13708 grad_norm: 6.7640 loss: 1.0829 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0829 2023/02/18 03:24:14 - mmengine - INFO - Epoch(train) [43][ 700/1320] lr: 2.0000e-03 eta: 0:42:25 time: 0.2569 data_time: 0.0109 memory: 13708 grad_norm: 6.9070 loss: 0.9748 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9748 2023/02/18 03:24:19 - mmengine - INFO - Epoch(train) [43][ 720/1320] lr: 2.0000e-03 eta: 0:42:20 time: 0.2568 data_time: 0.0117 memory: 13708 grad_norm: 7.1008 loss: 1.1072 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1072 2023/02/18 03:24:24 - mmengine - INFO - Epoch(train) [43][ 740/1320] lr: 2.0000e-03 eta: 0:42:14 time: 0.2602 data_time: 0.0150 memory: 13708 grad_norm: 6.8437 loss: 0.9991 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9991 2023/02/18 03:24:29 - mmengine - INFO - Epoch(train) [43][ 760/1320] lr: 2.0000e-03 eta: 0:42:09 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 7.1137 loss: 0.9487 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 0.9487 2023/02/18 03:24:34 - mmengine - INFO - Epoch(train) [43][ 780/1320] lr: 2.0000e-03 eta: 0:42:04 time: 0.2569 data_time: 0.0106 memory: 13708 grad_norm: 7.1397 loss: 1.0472 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0472 2023/02/18 03:24:39 - mmengine - INFO - Epoch(train) [43][ 800/1320] lr: 2.0000e-03 eta: 0:41:59 time: 0.2567 data_time: 0.0110 memory: 13708 grad_norm: 7.1681 loss: 0.9304 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9304 2023/02/18 03:24:44 - mmengine - INFO - Epoch(train) [43][ 820/1320] lr: 2.0000e-03 eta: 0:41:54 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 6.7533 loss: 1.0375 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0375 2023/02/18 03:24:50 - mmengine - INFO - Epoch(train) [43][ 840/1320] lr: 2.0000e-03 eta: 0:41:49 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 6.8790 loss: 1.0349 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.0349 2023/02/18 03:24:55 - mmengine - INFO - Epoch(train) [43][ 860/1320] lr: 2.0000e-03 eta: 0:41:43 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 7.1079 loss: 1.2390 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2390 2023/02/18 03:25:00 - mmengine - INFO - Epoch(train) [43][ 880/1320] lr: 2.0000e-03 eta: 0:41:38 time: 0.2569 data_time: 0.0109 memory: 13708 grad_norm: 7.0391 loss: 0.8956 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8956 2023/02/18 03:25:05 - mmengine - INFO - Epoch(train) [43][ 900/1320] lr: 2.0000e-03 eta: 0:41:33 time: 0.2565 data_time: 0.0112 memory: 13708 grad_norm: 6.9574 loss: 1.0960 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.0960 2023/02/18 03:25:10 - mmengine - INFO - Epoch(train) [43][ 920/1320] lr: 2.0000e-03 eta: 0:41:28 time: 0.2558 data_time: 0.0111 memory: 13708 grad_norm: 6.9011 loss: 0.9865 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9865 2023/02/18 03:25:15 - mmengine - INFO - Epoch(train) [43][ 940/1320] lr: 2.0000e-03 eta: 0:41:23 time: 0.2560 data_time: 0.0106 memory: 13708 grad_norm: 7.0834 loss: 0.9425 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9425 2023/02/18 03:25:20 - mmengine - INFO - Epoch(train) [43][ 960/1320] lr: 2.0000e-03 eta: 0:41:18 time: 0.2575 data_time: 0.0120 memory: 13708 grad_norm: 7.0768 loss: 1.2293 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.2293 2023/02/18 03:25:26 - mmengine - INFO - Epoch(train) [43][ 980/1320] lr: 2.0000e-03 eta: 0:41:12 time: 0.2566 data_time: 0.0116 memory: 13708 grad_norm: 7.0400 loss: 0.9780 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9780 2023/02/18 03:25:31 - mmengine - INFO - Epoch(train) [43][1000/1320] lr: 2.0000e-03 eta: 0:41:07 time: 0.2567 data_time: 0.0108 memory: 13708 grad_norm: 7.3332 loss: 1.1935 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1935 2023/02/18 03:25:36 - mmengine - INFO - Epoch(train) [43][1020/1320] lr: 2.0000e-03 eta: 0:41:02 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 7.0280 loss: 1.1481 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.1481 2023/02/18 03:25:41 - mmengine - INFO - Epoch(train) [43][1040/1320] lr: 2.0000e-03 eta: 0:40:57 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 6.9738 loss: 1.1336 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1336 2023/02/18 03:25:46 - mmengine - INFO - Epoch(train) [43][1060/1320] lr: 2.0000e-03 eta: 0:40:52 time: 0.2558 data_time: 0.0106 memory: 13708 grad_norm: 7.1499 loss: 1.1414 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1414 2023/02/18 03:25:51 - mmengine - INFO - Epoch(train) [43][1080/1320] lr: 2.0000e-03 eta: 0:40:47 time: 0.2567 data_time: 0.0112 memory: 13708 grad_norm: 7.0370 loss: 1.0411 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0411 2023/02/18 03:25:56 - mmengine - INFO - Epoch(train) [43][1100/1320] lr: 2.0000e-03 eta: 0:40:41 time: 0.2564 data_time: 0.0106 memory: 13708 grad_norm: 7.1350 loss: 1.0319 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0319 2023/02/18 03:26:01 - mmengine - INFO - Epoch(train) [43][1120/1320] lr: 2.0000e-03 eta: 0:40:36 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 7.1328 loss: 1.0543 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0543 2023/02/18 03:26:07 - mmengine - INFO - Epoch(train) [43][1140/1320] lr: 2.0000e-03 eta: 0:40:31 time: 0.2562 data_time: 0.0106 memory: 13708 grad_norm: 7.4723 loss: 1.3285 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3285 2023/02/18 03:26:12 - mmengine - INFO - Epoch(train) [43][1160/1320] lr: 2.0000e-03 eta: 0:40:26 time: 0.2568 data_time: 0.0111 memory: 13708 grad_norm: 7.1039 loss: 1.2690 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.2690 2023/02/18 03:26:17 - mmengine - INFO - Epoch(train) [43][1180/1320] lr: 2.0000e-03 eta: 0:40:21 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 7.2106 loss: 1.0393 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0393 2023/02/18 03:26:22 - mmengine - INFO - Epoch(train) [43][1200/1320] lr: 2.0000e-03 eta: 0:40:16 time: 0.2556 data_time: 0.0102 memory: 13708 grad_norm: 7.0157 loss: 1.1609 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1609 2023/02/18 03:26:27 - mmengine - INFO - Epoch(train) [43][1220/1320] lr: 2.0000e-03 eta: 0:40:10 time: 0.2564 data_time: 0.0112 memory: 13708 grad_norm: 7.0255 loss: 1.0003 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0003 2023/02/18 03:26:32 - mmengine - INFO - Epoch(train) [43][1240/1320] lr: 2.0000e-03 eta: 0:40:05 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 7.0421 loss: 1.1086 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.1086 2023/02/18 03:26:37 - mmengine - INFO - Epoch(train) [43][1260/1320] lr: 2.0000e-03 eta: 0:40:00 time: 0.2560 data_time: 0.0107 memory: 13708 grad_norm: 6.7968 loss: 1.1973 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.1973 2023/02/18 03:26:42 - mmengine - INFO - Epoch(train) [43][1280/1320] lr: 2.0000e-03 eta: 0:39:55 time: 0.2567 data_time: 0.0109 memory: 13708 grad_norm: 7.0019 loss: 1.0665 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0665 2023/02/18 03:26:48 - mmengine - INFO - Epoch(train) [43][1300/1320] lr: 2.0000e-03 eta: 0:39:50 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 7.1984 loss: 1.1093 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1093 2023/02/18 03:26:53 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:26:53 - mmengine - INFO - Epoch(train) [43][1320/1320] lr: 2.0000e-03 eta: 0:39:44 time: 0.2534 data_time: 0.0130 memory: 13708 grad_norm: 7.0269 loss: 1.1642 top1_acc: 0.5455 top5_acc: 0.9091 loss_cls: 1.1642 2023/02/18 03:26:55 - mmengine - INFO - Epoch(val) [43][ 20/194] eta: 0:00:22 time: 0.1275 data_time: 0.0588 memory: 1818 2023/02/18 03:26:57 - mmengine - INFO - Epoch(val) [43][ 40/194] eta: 0:00:16 time: 0.0894 data_time: 0.0217 memory: 1818 2023/02/18 03:26:59 - mmengine - INFO - Epoch(val) [43][ 60/194] eta: 0:00:13 time: 0.0958 data_time: 0.0275 memory: 1818 2023/02/18 03:27:01 - mmengine - INFO - Epoch(val) [43][ 80/194] eta: 0:00:11 time: 0.0838 data_time: 0.0162 memory: 1818 2023/02/18 03:27:03 - mmengine - INFO - Epoch(val) [43][100/194] eta: 0:00:09 time: 0.0935 data_time: 0.0251 memory: 1818 2023/02/18 03:27:04 - mmengine - INFO - Epoch(val) [43][120/194] eta: 0:00:07 time: 0.0833 data_time: 0.0156 memory: 1818 2023/02/18 03:27:06 - mmengine - INFO - Epoch(val) [43][140/194] eta: 0:00:05 time: 0.1010 data_time: 0.0326 memory: 1818 2023/02/18 03:27:08 - mmengine - INFO - Epoch(val) [43][160/194] eta: 0:00:03 time: 0.0796 data_time: 0.0121 memory: 1818 2023/02/18 03:27:10 - mmengine - INFO - Epoch(val) [43][180/194] eta: 0:00:01 time: 0.0868 data_time: 0.0178 memory: 1818 2023/02/18 03:27:11 - mmengine - INFO - Epoch(val) [43][194/194] acc/top1: 0.5851 acc/top5: 0.8535 acc/mean1: 0.5172 2023/02/18 03:27:17 - mmengine - INFO - Epoch(train) [44][ 20/1320] lr: 2.0000e-03 eta: 0:39:39 time: 0.3021 data_time: 0.0444 memory: 13708 grad_norm: 6.9432 loss: 1.0103 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0103 2023/02/18 03:27:22 - mmengine - INFO - Epoch(train) [44][ 40/1320] lr: 2.0000e-03 eta: 0:39:34 time: 0.2576 data_time: 0.0108 memory: 13708 grad_norm: 6.9175 loss: 1.0978 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0978 2023/02/18 03:27:28 - mmengine - INFO - Epoch(train) [44][ 60/1320] lr: 2.0000e-03 eta: 0:39:29 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 6.8929 loss: 0.8906 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 0.8906 2023/02/18 03:27:33 - mmengine - INFO - Epoch(train) [44][ 80/1320] lr: 2.0000e-03 eta: 0:39:24 time: 0.2564 data_time: 0.0115 memory: 13708 grad_norm: 6.9754 loss: 1.1965 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1965 2023/02/18 03:27:38 - mmengine - INFO - Epoch(train) [44][ 100/1320] lr: 2.0000e-03 eta: 0:39:19 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 6.8818 loss: 1.0061 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0061 2023/02/18 03:27:43 - mmengine - INFO - Epoch(train) [44][ 120/1320] lr: 2.0000e-03 eta: 0:39:14 time: 0.2577 data_time: 0.0114 memory: 13708 grad_norm: 7.1174 loss: 1.0238 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0238 2023/02/18 03:27:48 - mmengine - INFO - Epoch(train) [44][ 140/1320] lr: 2.0000e-03 eta: 0:39:08 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 6.9188 loss: 1.0539 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0539 2023/02/18 03:27:53 - mmengine - INFO - Epoch(train) [44][ 160/1320] lr: 2.0000e-03 eta: 0:39:03 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 7.1733 loss: 1.1773 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1773 2023/02/18 03:27:58 - mmengine - INFO - Epoch(train) [44][ 180/1320] lr: 2.0000e-03 eta: 0:38:58 time: 0.2577 data_time: 0.0123 memory: 13708 grad_norm: 7.0383 loss: 1.2146 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2146 2023/02/18 03:28:04 - mmengine - INFO - Epoch(train) [44][ 200/1320] lr: 2.0000e-03 eta: 0:38:53 time: 0.2558 data_time: 0.0105 memory: 13708 grad_norm: 6.9603 loss: 1.0181 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.0181 2023/02/18 03:28:09 - mmengine - INFO - Epoch(train) [44][ 220/1320] lr: 2.0000e-03 eta: 0:38:48 time: 0.2573 data_time: 0.0110 memory: 13708 grad_norm: 6.8870 loss: 0.9104 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9104 2023/02/18 03:28:14 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:28:14 - mmengine - INFO - Epoch(train) [44][ 240/1320] lr: 2.0000e-03 eta: 0:38:43 time: 0.2570 data_time: 0.0114 memory: 13708 grad_norm: 6.8389 loss: 1.0244 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0244 2023/02/18 03:28:19 - mmengine - INFO - Epoch(train) [44][ 260/1320] lr: 2.0000e-03 eta: 0:38:37 time: 0.2566 data_time: 0.0108 memory: 13708 grad_norm: 6.8574 loss: 0.9683 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9683 2023/02/18 03:28:24 - mmengine - INFO - Epoch(train) [44][ 280/1320] lr: 2.0000e-03 eta: 0:38:32 time: 0.2574 data_time: 0.0122 memory: 13708 grad_norm: 7.0144 loss: 1.1062 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1062 2023/02/18 03:28:29 - mmengine - INFO - Epoch(train) [44][ 300/1320] lr: 2.0000e-03 eta: 0:38:27 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 7.0877 loss: 0.9512 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9512 2023/02/18 03:28:34 - mmengine - INFO - Epoch(train) [44][ 320/1320] lr: 2.0000e-03 eta: 0:38:22 time: 0.2560 data_time: 0.0106 memory: 13708 grad_norm: 7.2741 loss: 1.1638 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1638 2023/02/18 03:28:39 - mmengine - INFO - Epoch(train) [44][ 340/1320] lr: 2.0000e-03 eta: 0:38:17 time: 0.2560 data_time: 0.0105 memory: 13708 grad_norm: 7.0723 loss: 1.0561 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0561 2023/02/18 03:28:45 - mmengine - INFO - Epoch(train) [44][ 360/1320] lr: 2.0000e-03 eta: 0:38:12 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 6.8310 loss: 1.0278 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0278 2023/02/18 03:28:50 - mmengine - INFO - Epoch(train) [44][ 380/1320] lr: 2.0000e-03 eta: 0:38:06 time: 0.2558 data_time: 0.0104 memory: 13708 grad_norm: 6.8772 loss: 1.0569 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0569 2023/02/18 03:28:55 - mmengine - INFO - Epoch(train) [44][ 400/1320] lr: 2.0000e-03 eta: 0:38:01 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 7.0534 loss: 1.0178 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0178 2023/02/18 03:29:00 - mmengine - INFO - Epoch(train) [44][ 420/1320] lr: 2.0000e-03 eta: 0:37:56 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 7.1050 loss: 1.0438 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0438 2023/02/18 03:29:05 - mmengine - INFO - Epoch(train) [44][ 440/1320] lr: 2.0000e-03 eta: 0:37:51 time: 0.2569 data_time: 0.0109 memory: 13708 grad_norm: 7.1533 loss: 1.0265 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0265 2023/02/18 03:29:10 - mmengine - INFO - Epoch(train) [44][ 460/1320] lr: 2.0000e-03 eta: 0:37:46 time: 0.2566 data_time: 0.0106 memory: 13708 grad_norm: 7.2591 loss: 1.1035 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1035 2023/02/18 03:29:15 - mmengine - INFO - Epoch(train) [44][ 480/1320] lr: 2.0000e-03 eta: 0:37:41 time: 0.2557 data_time: 0.0111 memory: 13708 grad_norm: 7.1264 loss: 0.9378 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 0.9378 2023/02/18 03:29:21 - mmengine - INFO - Epoch(train) [44][ 500/1320] lr: 2.0000e-03 eta: 0:37:35 time: 0.2567 data_time: 0.0104 memory: 13708 grad_norm: 7.2036 loss: 0.8258 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.8258 2023/02/18 03:29:26 - mmengine - INFO - Epoch(train) [44][ 520/1320] lr: 2.0000e-03 eta: 0:37:30 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 7.1787 loss: 1.1206 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1206 2023/02/18 03:29:31 - mmengine - INFO - Epoch(train) [44][ 540/1320] lr: 2.0000e-03 eta: 0:37:25 time: 0.2561 data_time: 0.0112 memory: 13708 grad_norm: 7.1254 loss: 1.0619 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0619 2023/02/18 03:29:36 - mmengine - INFO - Epoch(train) [44][ 560/1320] lr: 2.0000e-03 eta: 0:37:20 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 7.2642 loss: 1.1250 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1250 2023/02/18 03:29:41 - mmengine - INFO - Epoch(train) [44][ 580/1320] lr: 2.0000e-03 eta: 0:37:15 time: 0.2560 data_time: 0.0107 memory: 13708 grad_norm: 7.0190 loss: 0.9382 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9382 2023/02/18 03:29:46 - mmengine - INFO - Epoch(train) [44][ 600/1320] lr: 2.0000e-03 eta: 0:37:10 time: 0.2561 data_time: 0.0112 memory: 13708 grad_norm: 7.2417 loss: 1.0535 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0535 2023/02/18 03:29:51 - mmengine - INFO - Epoch(train) [44][ 620/1320] lr: 2.0000e-03 eta: 0:37:04 time: 0.2560 data_time: 0.0105 memory: 13708 grad_norm: 7.3172 loss: 1.0516 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0516 2023/02/18 03:29:56 - mmengine - INFO - Epoch(train) [44][ 640/1320] lr: 2.0000e-03 eta: 0:36:59 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 6.9927 loss: 1.0467 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0467 2023/02/18 03:30:02 - mmengine - INFO - Epoch(train) [44][ 660/1320] lr: 2.0000e-03 eta: 0:36:54 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 7.1785 loss: 1.0295 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.0295 2023/02/18 03:30:07 - mmengine - INFO - Epoch(train) [44][ 680/1320] lr: 2.0000e-03 eta: 0:36:49 time: 0.2569 data_time: 0.0116 memory: 13708 grad_norm: 7.2103 loss: 1.0885 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0885 2023/02/18 03:30:12 - mmengine - INFO - Epoch(train) [44][ 700/1320] lr: 2.0000e-03 eta: 0:36:44 time: 0.2564 data_time: 0.0107 memory: 13708 grad_norm: 7.0778 loss: 1.1453 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1453 2023/02/18 03:30:17 - mmengine - INFO - Epoch(train) [44][ 720/1320] lr: 2.0000e-03 eta: 0:36:39 time: 0.2563 data_time: 0.0114 memory: 13708 grad_norm: 7.0453 loss: 0.9517 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9517 2023/02/18 03:30:22 - mmengine - INFO - Epoch(train) [44][ 740/1320] lr: 2.0000e-03 eta: 0:36:33 time: 0.2561 data_time: 0.0105 memory: 13708 grad_norm: 7.2992 loss: 0.9852 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9852 2023/02/18 03:30:27 - mmengine - INFO - Epoch(train) [44][ 760/1320] lr: 2.0000e-03 eta: 0:36:28 time: 0.2567 data_time: 0.0113 memory: 13708 grad_norm: 7.1886 loss: 1.0761 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0761 2023/02/18 03:30:32 - mmengine - INFO - Epoch(train) [44][ 780/1320] lr: 2.0000e-03 eta: 0:36:23 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 7.2056 loss: 1.1996 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1996 2023/02/18 03:30:37 - mmengine - INFO - Epoch(train) [44][ 800/1320] lr: 2.0000e-03 eta: 0:36:18 time: 0.2564 data_time: 0.0108 memory: 13708 grad_norm: 7.1945 loss: 1.0928 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0928 2023/02/18 03:30:43 - mmengine - INFO - Epoch(train) [44][ 820/1320] lr: 2.0000e-03 eta: 0:36:13 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 7.1505 loss: 1.1119 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1119 2023/02/18 03:30:48 - mmengine - INFO - Epoch(train) [44][ 840/1320] lr: 2.0000e-03 eta: 0:36:08 time: 0.2570 data_time: 0.0107 memory: 13708 grad_norm: 7.2674 loss: 1.1872 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1872 2023/02/18 03:30:53 - mmengine - INFO - Epoch(train) [44][ 860/1320] lr: 2.0000e-03 eta: 0:36:02 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 7.1563 loss: 1.1103 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1103 2023/02/18 03:30:58 - mmengine - INFO - Epoch(train) [44][ 880/1320] lr: 2.0000e-03 eta: 0:35:57 time: 0.2557 data_time: 0.0110 memory: 13708 grad_norm: 7.2808 loss: 1.1046 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.1046 2023/02/18 03:31:03 - mmengine - INFO - Epoch(train) [44][ 900/1320] lr: 2.0000e-03 eta: 0:35:52 time: 0.2567 data_time: 0.0116 memory: 13708 grad_norm: 7.1440 loss: 1.1105 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1105 2023/02/18 03:31:08 - mmengine - INFO - Epoch(train) [44][ 920/1320] lr: 2.0000e-03 eta: 0:35:47 time: 0.2566 data_time: 0.0107 memory: 13708 grad_norm: 7.3437 loss: 0.9304 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9304 2023/02/18 03:31:13 - mmengine - INFO - Epoch(train) [44][ 940/1320] lr: 2.0000e-03 eta: 0:35:42 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 7.1934 loss: 1.0639 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0639 2023/02/18 03:31:18 - mmengine - INFO - Epoch(train) [44][ 960/1320] lr: 2.0000e-03 eta: 0:35:37 time: 0.2578 data_time: 0.0115 memory: 13708 grad_norm: 7.1347 loss: 0.9612 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9612 2023/02/18 03:31:24 - mmengine - INFO - Epoch(train) [44][ 980/1320] lr: 2.0000e-03 eta: 0:35:31 time: 0.2566 data_time: 0.0114 memory: 13708 grad_norm: 7.0448 loss: 1.1703 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.1703 2023/02/18 03:31:29 - mmengine - INFO - Epoch(train) [44][1000/1320] lr: 2.0000e-03 eta: 0:35:26 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 7.4285 loss: 1.1564 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1564 2023/02/18 03:31:34 - mmengine - INFO - Epoch(train) [44][1020/1320] lr: 2.0000e-03 eta: 0:35:21 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 7.2693 loss: 0.9734 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 0.9734 2023/02/18 03:31:39 - mmengine - INFO - Epoch(train) [44][1040/1320] lr: 2.0000e-03 eta: 0:35:16 time: 0.2571 data_time: 0.0123 memory: 13708 grad_norm: 7.3837 loss: 1.0981 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.0981 2023/02/18 03:31:44 - mmengine - INFO - Epoch(train) [44][1060/1320] lr: 2.0000e-03 eta: 0:35:11 time: 0.2567 data_time: 0.0101 memory: 13708 grad_norm: 7.2743 loss: 0.9618 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9618 2023/02/18 03:31:49 - mmengine - INFO - Epoch(train) [44][1080/1320] lr: 2.0000e-03 eta: 0:35:06 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 7.2195 loss: 1.0351 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0351 2023/02/18 03:31:54 - mmengine - INFO - Epoch(train) [44][1100/1320] lr: 2.0000e-03 eta: 0:35:00 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 7.2847 loss: 1.2081 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2081 2023/02/18 03:32:00 - mmengine - INFO - Epoch(train) [44][1120/1320] lr: 2.0000e-03 eta: 0:34:55 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 7.0731 loss: 1.0348 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0348 2023/02/18 03:32:05 - mmengine - INFO - Epoch(train) [44][1140/1320] lr: 2.0000e-03 eta: 0:34:50 time: 0.2572 data_time: 0.0112 memory: 13708 grad_norm: 7.2946 loss: 1.0180 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0180 2023/02/18 03:32:10 - mmengine - INFO - Epoch(train) [44][1160/1320] lr: 2.0000e-03 eta: 0:34:45 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 7.1308 loss: 0.8579 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8579 2023/02/18 03:32:15 - mmengine - INFO - Epoch(train) [44][1180/1320] lr: 2.0000e-03 eta: 0:34:40 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 7.3139 loss: 1.0680 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0680 2023/02/18 03:32:20 - mmengine - INFO - Epoch(train) [44][1200/1320] lr: 2.0000e-03 eta: 0:34:35 time: 0.2566 data_time: 0.0110 memory: 13708 grad_norm: 7.3269 loss: 1.0786 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0786 2023/02/18 03:32:25 - mmengine - INFO - Epoch(train) [44][1220/1320] lr: 2.0000e-03 eta: 0:34:29 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 7.1566 loss: 1.2695 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2695 2023/02/18 03:32:30 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:32:30 - mmengine - INFO - Epoch(train) [44][1240/1320] lr: 2.0000e-03 eta: 0:34:24 time: 0.2566 data_time: 0.0113 memory: 13708 grad_norm: 7.2048 loss: 1.0658 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0658 2023/02/18 03:32:35 - mmengine - INFO - Epoch(train) [44][1260/1320] lr: 2.0000e-03 eta: 0:34:19 time: 0.2568 data_time: 0.0110 memory: 13708 grad_norm: 7.2826 loss: 0.9523 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9523 2023/02/18 03:32:41 - mmengine - INFO - Epoch(train) [44][1280/1320] lr: 2.0000e-03 eta: 0:34:14 time: 0.2558 data_time: 0.0105 memory: 13708 grad_norm: 6.9640 loss: 1.0041 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0041 2023/02/18 03:32:46 - mmengine - INFO - Epoch(train) [44][1300/1320] lr: 2.0000e-03 eta: 0:34:09 time: 0.2571 data_time: 0.0109 memory: 13708 grad_norm: 7.1936 loss: 0.9721 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9721 2023/02/18 03:32:51 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:32:51 - mmengine - INFO - Epoch(train) [44][1320/1320] lr: 2.0000e-03 eta: 0:34:04 time: 0.2520 data_time: 0.0103 memory: 13708 grad_norm: 7.3748 loss: 1.2452 top1_acc: 0.6364 top5_acc: 0.9091 loss_cls: 1.2452 2023/02/18 03:32:53 - mmengine - INFO - Epoch(val) [44][ 20/194] eta: 0:00:21 time: 0.1232 data_time: 0.0544 memory: 1818 2023/02/18 03:32:55 - mmengine - INFO - Epoch(val) [44][ 40/194] eta: 0:00:16 time: 0.0878 data_time: 0.0194 memory: 1818 2023/02/18 03:32:57 - mmengine - INFO - Epoch(val) [44][ 60/194] eta: 0:00:13 time: 0.0892 data_time: 0.0202 memory: 1818 2023/02/18 03:32:58 - mmengine - INFO - Epoch(val) [44][ 80/194] eta: 0:00:10 time: 0.0843 data_time: 0.0160 memory: 1818 2023/02/18 03:33:00 - mmengine - INFO - Epoch(val) [44][100/194] eta: 0:00:08 time: 0.0924 data_time: 0.0227 memory: 1818 2023/02/18 03:33:02 - mmengine - INFO - Epoch(val) [44][120/194] eta: 0:00:06 time: 0.0851 data_time: 0.0167 memory: 1818 2023/02/18 03:33:04 - mmengine - INFO - Epoch(val) [44][140/194] eta: 0:00:05 time: 0.0898 data_time: 0.0198 memory: 1818 2023/02/18 03:33:05 - mmengine - INFO - Epoch(val) [44][160/194] eta: 0:00:03 time: 0.0822 data_time: 0.0135 memory: 1818 2023/02/18 03:33:07 - mmengine - INFO - Epoch(val) [44][180/194] eta: 0:00:01 time: 0.0854 data_time: 0.0162 memory: 1818 2023/02/18 03:33:09 - mmengine - INFO - Epoch(val) [44][194/194] acc/top1: 0.5839 acc/top5: 0.8513 acc/mean1: 0.5180 2023/02/18 03:33:15 - mmengine - INFO - Epoch(train) [45][ 20/1320] lr: 2.0000e-03 eta: 0:33:59 time: 0.2985 data_time: 0.0439 memory: 13708 grad_norm: 6.8611 loss: 0.9257 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9257 2023/02/18 03:33:20 - mmengine - INFO - Epoch(train) [45][ 40/1320] lr: 2.0000e-03 eta: 0:33:53 time: 0.2569 data_time: 0.0111 memory: 13708 grad_norm: 6.9373 loss: 1.0489 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0489 2023/02/18 03:33:25 - mmengine - INFO - Epoch(train) [45][ 60/1320] lr: 2.0000e-03 eta: 0:33:48 time: 0.2554 data_time: 0.0108 memory: 13708 grad_norm: 6.8843 loss: 0.8995 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.8995 2023/02/18 03:33:31 - mmengine - INFO - Epoch(train) [45][ 80/1320] lr: 2.0000e-03 eta: 0:33:43 time: 0.2555 data_time: 0.0107 memory: 13708 grad_norm: 7.0475 loss: 0.8549 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8549 2023/02/18 03:33:36 - mmengine - INFO - Epoch(train) [45][ 100/1320] lr: 2.0000e-03 eta: 0:33:38 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 7.1499 loss: 0.9643 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.9643 2023/02/18 03:33:41 - mmengine - INFO - Epoch(train) [45][ 120/1320] lr: 2.0000e-03 eta: 0:33:33 time: 0.2574 data_time: 0.0108 memory: 13708 grad_norm: 7.1351 loss: 0.9180 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9180 2023/02/18 03:33:46 - mmengine - INFO - Epoch(train) [45][ 140/1320] lr: 2.0000e-03 eta: 0:33:28 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 7.1374 loss: 1.0633 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.0633 2023/02/18 03:33:51 - mmengine - INFO - Epoch(train) [45][ 160/1320] lr: 2.0000e-03 eta: 0:33:22 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 7.2316 loss: 1.0855 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0855 2023/02/18 03:33:56 - mmengine - INFO - Epoch(train) [45][ 180/1320] lr: 2.0000e-03 eta: 0:33:17 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 7.2376 loss: 1.0414 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.0414 2023/02/18 03:34:01 - mmengine - INFO - Epoch(train) [45][ 200/1320] lr: 2.0000e-03 eta: 0:33:12 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 6.9573 loss: 1.0210 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0210 2023/02/18 03:34:06 - mmengine - INFO - Epoch(train) [45][ 220/1320] lr: 2.0000e-03 eta: 0:33:07 time: 0.2570 data_time: 0.0114 memory: 13708 grad_norm: 6.8552 loss: 0.9656 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9656 2023/02/18 03:34:12 - mmengine - INFO - Epoch(train) [45][ 240/1320] lr: 2.0000e-03 eta: 0:33:02 time: 0.2564 data_time: 0.0114 memory: 13708 grad_norm: 7.2925 loss: 0.9162 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9162 2023/02/18 03:34:17 - mmengine - INFO - Epoch(train) [45][ 260/1320] lr: 2.0000e-03 eta: 0:32:57 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 7.2033 loss: 0.9873 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 0.9873 2023/02/18 03:34:22 - mmengine - INFO - Epoch(train) [45][ 280/1320] lr: 2.0000e-03 eta: 0:32:51 time: 0.2568 data_time: 0.0114 memory: 13708 grad_norm: 7.3804 loss: 1.0825 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0825 2023/02/18 03:34:27 - mmengine - INFO - Epoch(train) [45][ 300/1320] lr: 2.0000e-03 eta: 0:32:46 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 7.3847 loss: 0.9741 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9741 2023/02/18 03:34:32 - mmengine - INFO - Epoch(train) [45][ 320/1320] lr: 2.0000e-03 eta: 0:32:41 time: 0.2560 data_time: 0.0106 memory: 13708 grad_norm: 7.4528 loss: 1.1203 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1203 2023/02/18 03:34:37 - mmengine - INFO - Epoch(train) [45][ 340/1320] lr: 2.0000e-03 eta: 0:32:36 time: 0.2566 data_time: 0.0112 memory: 13708 grad_norm: 7.3675 loss: 1.0288 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0288 2023/02/18 03:34:42 - mmengine - INFO - Epoch(train) [45][ 360/1320] lr: 2.0000e-03 eta: 0:32:31 time: 0.2572 data_time: 0.0126 memory: 13708 grad_norm: 7.2855 loss: 1.0884 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.0884 2023/02/18 03:34:47 - mmengine - INFO - Epoch(train) [45][ 380/1320] lr: 2.0000e-03 eta: 0:32:26 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 7.3212 loss: 1.0167 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0167 2023/02/18 03:34:53 - mmengine - INFO - Epoch(train) [45][ 400/1320] lr: 2.0000e-03 eta: 0:32:20 time: 0.2568 data_time: 0.0113 memory: 13708 grad_norm: 7.4538 loss: 1.0223 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0223 2023/02/18 03:34:58 - mmengine - INFO - Epoch(train) [45][ 420/1320] lr: 2.0000e-03 eta: 0:32:15 time: 0.2568 data_time: 0.0112 memory: 13708 grad_norm: 7.2151 loss: 1.0172 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0172 2023/02/18 03:35:03 - mmengine - INFO - Epoch(train) [45][ 440/1320] lr: 2.0000e-03 eta: 0:32:10 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 7.0857 loss: 1.0356 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0356 2023/02/18 03:35:08 - mmengine - INFO - Epoch(train) [45][ 460/1320] lr: 2.0000e-03 eta: 0:32:05 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 6.9897 loss: 0.9437 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9437 2023/02/18 03:35:13 - mmengine - INFO - Epoch(train) [45][ 480/1320] lr: 2.0000e-03 eta: 0:32:00 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 7.3629 loss: 0.9953 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9953 2023/02/18 03:35:18 - mmengine - INFO - Epoch(train) [45][ 500/1320] lr: 2.0000e-03 eta: 0:31:55 time: 0.2562 data_time: 0.0115 memory: 13708 grad_norm: 7.3487 loss: 0.8822 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 0.8822 2023/02/18 03:35:23 - mmengine - INFO - Epoch(train) [45][ 520/1320] lr: 2.0000e-03 eta: 0:31:49 time: 0.2578 data_time: 0.0125 memory: 13708 grad_norm: 7.4219 loss: 1.0017 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0017 2023/02/18 03:35:29 - mmengine - INFO - Epoch(train) [45][ 540/1320] lr: 2.0000e-03 eta: 0:31:44 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 7.1921 loss: 1.0282 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0282 2023/02/18 03:35:34 - mmengine - INFO - Epoch(train) [45][ 560/1320] lr: 2.0000e-03 eta: 0:31:39 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 7.2995 loss: 0.9468 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9468 2023/02/18 03:35:39 - mmengine - INFO - Epoch(train) [45][ 580/1320] lr: 2.0000e-03 eta: 0:31:34 time: 0.2558 data_time: 0.0105 memory: 13708 grad_norm: 7.5739 loss: 1.2653 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2653 2023/02/18 03:35:44 - mmengine - INFO - Epoch(train) [45][ 600/1320] lr: 2.0000e-03 eta: 0:31:29 time: 0.2559 data_time: 0.0106 memory: 13708 grad_norm: 7.2660 loss: 1.0951 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0951 2023/02/18 03:35:49 - mmengine - INFO - Epoch(train) [45][ 620/1320] lr: 2.0000e-03 eta: 0:31:24 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 7.1536 loss: 1.1072 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.1072 2023/02/18 03:35:54 - mmengine - INFO - Epoch(train) [45][ 640/1320] lr: 2.0000e-03 eta: 0:31:18 time: 0.2559 data_time: 0.0105 memory: 13708 grad_norm: 7.1995 loss: 1.0943 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.0943 2023/02/18 03:35:59 - mmengine - INFO - Epoch(train) [45][ 660/1320] lr: 2.0000e-03 eta: 0:31:13 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 7.2331 loss: 0.8341 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8341 2023/02/18 03:36:04 - mmengine - INFO - Epoch(train) [45][ 680/1320] lr: 2.0000e-03 eta: 0:31:08 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 7.2988 loss: 1.0135 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0135 2023/02/18 03:36:10 - mmengine - INFO - Epoch(train) [45][ 700/1320] lr: 2.0000e-03 eta: 0:31:03 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 7.2752 loss: 1.1664 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1664 2023/02/18 03:36:15 - mmengine - INFO - Epoch(train) [45][ 720/1320] lr: 2.0000e-03 eta: 0:30:58 time: 0.2566 data_time: 0.0111 memory: 13708 grad_norm: 7.0869 loss: 0.9938 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9938 2023/02/18 03:36:20 - mmengine - INFO - Epoch(train) [45][ 740/1320] lr: 2.0000e-03 eta: 0:30:53 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 7.3128 loss: 1.0021 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.0021 2023/02/18 03:36:25 - mmengine - INFO - Epoch(train) [45][ 760/1320] lr: 2.0000e-03 eta: 0:30:47 time: 0.2568 data_time: 0.0110 memory: 13708 grad_norm: 7.5532 loss: 0.9863 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 0.9863 2023/02/18 03:36:30 - mmengine - INFO - Epoch(train) [45][ 780/1320] lr: 2.0000e-03 eta: 0:30:42 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 7.3897 loss: 1.0022 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0022 2023/02/18 03:36:35 - mmengine - INFO - Epoch(train) [45][ 800/1320] lr: 2.0000e-03 eta: 0:30:37 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 7.3822 loss: 0.9871 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.9871 2023/02/18 03:36:40 - mmengine - INFO - Epoch(train) [45][ 820/1320] lr: 2.0000e-03 eta: 0:30:32 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 7.4193 loss: 1.0598 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.0598 2023/02/18 03:36:45 - mmengine - INFO - Epoch(train) [45][ 840/1320] lr: 2.0000e-03 eta: 0:30:27 time: 0.2573 data_time: 0.0119 memory: 13708 grad_norm: 7.4146 loss: 1.1231 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1231 2023/02/18 03:36:51 - mmengine - INFO - Epoch(train) [45][ 860/1320] lr: 2.0000e-03 eta: 0:30:22 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 7.6233 loss: 1.1881 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1881 2023/02/18 03:36:56 - mmengine - INFO - Epoch(train) [45][ 880/1320] lr: 2.0000e-03 eta: 0:30:16 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 7.0631 loss: 0.8779 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 0.8779 2023/02/18 03:37:01 - mmengine - INFO - Epoch(train) [45][ 900/1320] lr: 2.0000e-03 eta: 0:30:11 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 7.3157 loss: 0.9342 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9342 2023/02/18 03:37:06 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:37:06 - mmengine - INFO - Epoch(train) [45][ 920/1320] lr: 2.0000e-03 eta: 0:30:06 time: 0.2576 data_time: 0.0126 memory: 13708 grad_norm: 7.4240 loss: 0.9794 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9794 2023/02/18 03:37:11 - mmengine - INFO - Epoch(train) [45][ 940/1320] lr: 2.0000e-03 eta: 0:30:01 time: 0.2566 data_time: 0.0110 memory: 13708 grad_norm: 7.2802 loss: 1.1423 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1423 2023/02/18 03:37:16 - mmengine - INFO - Epoch(train) [45][ 960/1320] lr: 2.0000e-03 eta: 0:29:56 time: 0.2555 data_time: 0.0104 memory: 13708 grad_norm: 7.3595 loss: 1.0499 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0499 2023/02/18 03:37:21 - mmengine - INFO - Epoch(train) [45][ 980/1320] lr: 2.0000e-03 eta: 0:29:51 time: 0.2569 data_time: 0.0113 memory: 13708 grad_norm: 7.1904 loss: 1.1035 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1035 2023/02/18 03:37:27 - mmengine - INFO - Epoch(train) [45][1000/1320] lr: 2.0000e-03 eta: 0:29:45 time: 0.2559 data_time: 0.0106 memory: 13708 grad_norm: 7.3356 loss: 0.9723 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9723 2023/02/18 03:37:32 - mmengine - INFO - Epoch(train) [45][1020/1320] lr: 2.0000e-03 eta: 0:29:40 time: 0.2571 data_time: 0.0114 memory: 13708 grad_norm: 7.6326 loss: 1.0705 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0705 2023/02/18 03:37:37 - mmengine - INFO - Epoch(train) [45][1040/1320] lr: 2.0000e-03 eta: 0:29:35 time: 0.2564 data_time: 0.0108 memory: 13708 grad_norm: 7.4571 loss: 1.1491 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1491 2023/02/18 03:37:42 - mmengine - INFO - Epoch(train) [45][1060/1320] lr: 2.0000e-03 eta: 0:29:30 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 7.7227 loss: 1.1016 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1016 2023/02/18 03:37:47 - mmengine - INFO - Epoch(train) [45][1080/1320] lr: 2.0000e-03 eta: 0:29:25 time: 0.2568 data_time: 0.0109 memory: 13708 grad_norm: 7.3056 loss: 1.1975 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1975 2023/02/18 03:37:52 - mmengine - INFO - Epoch(train) [45][1100/1320] lr: 2.0000e-03 eta: 0:29:20 time: 0.2563 data_time: 0.0112 memory: 13708 grad_norm: 7.2458 loss: 0.9622 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.9622 2023/02/18 03:37:57 - mmengine - INFO - Epoch(train) [45][1120/1320] lr: 2.0000e-03 eta: 0:29:14 time: 0.2557 data_time: 0.0112 memory: 13708 grad_norm: 7.3680 loss: 1.0395 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0395 2023/02/18 03:38:02 - mmengine - INFO - Epoch(train) [45][1140/1320] lr: 2.0000e-03 eta: 0:29:09 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 7.4084 loss: 1.0691 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0691 2023/02/18 03:38:08 - mmengine - INFO - Epoch(train) [45][1160/1320] lr: 2.0000e-03 eta: 0:29:04 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 7.5024 loss: 1.1274 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.1274 2023/02/18 03:38:13 - mmengine - INFO - Epoch(train) [45][1180/1320] lr: 2.0000e-03 eta: 0:28:59 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 7.5078 loss: 1.0942 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0942 2023/02/18 03:38:18 - mmengine - INFO - Epoch(train) [45][1200/1320] lr: 2.0000e-03 eta: 0:28:54 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 7.5643 loss: 1.0132 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0132 2023/02/18 03:38:23 - mmengine - INFO - Epoch(train) [45][1220/1320] lr: 2.0000e-03 eta: 0:28:49 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 7.4960 loss: 0.9500 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9500 2023/02/18 03:38:28 - mmengine - INFO - Epoch(train) [45][1240/1320] lr: 2.0000e-03 eta: 0:28:43 time: 0.2567 data_time: 0.0113 memory: 13708 grad_norm: 7.3189 loss: 0.9575 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9575 2023/02/18 03:38:33 - mmengine - INFO - Epoch(train) [45][1260/1320] lr: 2.0000e-03 eta: 0:28:38 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 7.3215 loss: 0.9874 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9874 2023/02/18 03:38:38 - mmengine - INFO - Epoch(train) [45][1280/1320] lr: 2.0000e-03 eta: 0:28:33 time: 0.2559 data_time: 0.0104 memory: 13708 grad_norm: 7.3742 loss: 1.0453 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0453 2023/02/18 03:38:43 - mmengine - INFO - Epoch(train) [45][1300/1320] lr: 2.0000e-03 eta: 0:28:28 time: 0.2574 data_time: 0.0121 memory: 13708 grad_norm: 7.3565 loss: 1.2119 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2119 2023/02/18 03:38:49 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:38:49 - mmengine - INFO - Epoch(train) [45][1320/1320] lr: 2.0000e-03 eta: 0:28:23 time: 0.2519 data_time: 0.0102 memory: 13708 grad_norm: 7.4474 loss: 1.1110 top1_acc: 0.5455 top5_acc: 1.0000 loss_cls: 1.1110 2023/02/18 03:38:49 - mmengine - INFO - Saving checkpoint at 45 epochs 2023/02/18 03:38:52 - mmengine - INFO - Epoch(val) [45][ 20/194] eta: 0:00:23 time: 0.1330 data_time: 0.0625 memory: 1818 2023/02/18 03:38:54 - mmengine - INFO - Epoch(val) [45][ 40/194] eta: 0:00:16 time: 0.0865 data_time: 0.0176 memory: 1818 2023/02/18 03:38:56 - mmengine - INFO - Epoch(val) [45][ 60/194] eta: 0:00:13 time: 0.0885 data_time: 0.0205 memory: 1818 2023/02/18 03:38:58 - mmengine - INFO - Epoch(val) [45][ 80/194] eta: 0:00:11 time: 0.0859 data_time: 0.0170 memory: 1818 2023/02/18 03:38:59 - mmengine - INFO - Epoch(val) [45][100/194] eta: 0:00:09 time: 0.0895 data_time: 0.0208 memory: 1818 2023/02/18 03:39:01 - mmengine - INFO - Epoch(val) [45][120/194] eta: 0:00:07 time: 0.0858 data_time: 0.0175 memory: 1818 2023/02/18 03:39:03 - mmengine - INFO - Epoch(val) [45][140/194] eta: 0:00:05 time: 0.0878 data_time: 0.0195 memory: 1818 2023/02/18 03:39:04 - mmengine - INFO - Epoch(val) [45][160/194] eta: 0:00:03 time: 0.0811 data_time: 0.0131 memory: 1818 2023/02/18 03:39:06 - mmengine - INFO - Epoch(val) [45][180/194] eta: 0:00:01 time: 0.0820 data_time: 0.0158 memory: 1818 2023/02/18 03:39:08 - mmengine - INFO - Epoch(val) [45][194/194] acc/top1: 0.5830 acc/top5: 0.8477 acc/mean1: 0.5227 2023/02/18 03:39:14 - mmengine - INFO - Epoch(train) [46][ 20/1320] lr: 2.0000e-04 eta: 0:28:18 time: 0.2981 data_time: 0.0423 memory: 13708 grad_norm: 7.2743 loss: 0.8286 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8286 2023/02/18 03:39:19 - mmengine - INFO - Epoch(train) [46][ 40/1320] lr: 2.0000e-04 eta: 0:28:12 time: 0.2567 data_time: 0.0109 memory: 13708 grad_norm: 7.1913 loss: 1.0271 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0271 2023/02/18 03:39:24 - mmengine - INFO - Epoch(train) [46][ 60/1320] lr: 2.0000e-04 eta: 0:28:07 time: 0.2560 data_time: 0.0104 memory: 13708 grad_norm: 6.9116 loss: 0.9401 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.9401 2023/02/18 03:39:29 - mmengine - INFO - Epoch(train) [46][ 80/1320] lr: 2.0000e-04 eta: 0:28:02 time: 0.2564 data_time: 0.0104 memory: 13708 grad_norm: 7.0731 loss: 1.0811 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0811 2023/02/18 03:39:34 - mmengine - INFO - Epoch(train) [46][ 100/1320] lr: 2.0000e-04 eta: 0:27:57 time: 0.2559 data_time: 0.0104 memory: 13708 grad_norm: 7.1347 loss: 1.0146 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0146 2023/02/18 03:39:39 - mmengine - INFO - Epoch(train) [46][ 120/1320] lr: 2.0000e-04 eta: 0:27:52 time: 0.2565 data_time: 0.0107 memory: 13708 grad_norm: 6.8659 loss: 0.8831 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8831 2023/02/18 03:39:45 - mmengine - INFO - Epoch(train) [46][ 140/1320] lr: 2.0000e-04 eta: 0:27:47 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 6.9896 loss: 0.8777 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8777 2023/02/18 03:39:50 - mmengine - INFO - Epoch(train) [46][ 160/1320] lr: 2.0000e-04 eta: 0:27:41 time: 0.2566 data_time: 0.0111 memory: 13708 grad_norm: 6.9848 loss: 1.0860 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0860 2023/02/18 03:39:55 - mmengine - INFO - Epoch(train) [46][ 180/1320] lr: 2.0000e-04 eta: 0:27:36 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 6.8665 loss: 0.9751 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9751 2023/02/18 03:40:00 - mmengine - INFO - Epoch(train) [46][ 200/1320] lr: 2.0000e-04 eta: 0:27:31 time: 0.2559 data_time: 0.0106 memory: 13708 grad_norm: 6.8944 loss: 0.9600 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9600 2023/02/18 03:40:05 - mmengine - INFO - Epoch(train) [46][ 220/1320] lr: 2.0000e-04 eta: 0:27:26 time: 0.2565 data_time: 0.0110 memory: 13708 grad_norm: 6.9329 loss: 0.8703 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8703 2023/02/18 03:40:10 - mmengine - INFO - Epoch(train) [46][ 240/1320] lr: 2.0000e-04 eta: 0:27:21 time: 0.2570 data_time: 0.0110 memory: 13708 grad_norm: 7.0950 loss: 1.0371 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0371 2023/02/18 03:40:15 - mmengine - INFO - Epoch(train) [46][ 260/1320] lr: 2.0000e-04 eta: 0:27:16 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 6.9544 loss: 0.9594 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9594 2023/02/18 03:40:20 - mmengine - INFO - Epoch(train) [46][ 280/1320] lr: 2.0000e-04 eta: 0:27:10 time: 0.2564 data_time: 0.0108 memory: 13708 grad_norm: 7.1600 loss: 0.9792 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 0.9792 2023/02/18 03:40:26 - mmengine - INFO - Epoch(train) [46][ 300/1320] lr: 2.0000e-04 eta: 0:27:05 time: 0.2565 data_time: 0.0106 memory: 13708 grad_norm: 7.0850 loss: 0.9742 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9742 2023/02/18 03:40:31 - mmengine - INFO - Epoch(train) [46][ 320/1320] lr: 2.0000e-04 eta: 0:27:00 time: 0.2565 data_time: 0.0111 memory: 13708 grad_norm: 6.8949 loss: 0.9654 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9654 2023/02/18 03:40:36 - mmengine - INFO - Epoch(train) [46][ 340/1320] lr: 2.0000e-04 eta: 0:26:55 time: 0.2568 data_time: 0.0105 memory: 13708 grad_norm: 7.1687 loss: 1.0755 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0755 2023/02/18 03:40:41 - mmengine - INFO - Epoch(train) [46][ 360/1320] lr: 2.0000e-04 eta: 0:26:50 time: 0.2564 data_time: 0.0108 memory: 13708 grad_norm: 6.9527 loss: 0.9357 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9357 2023/02/18 03:40:46 - mmengine - INFO - Epoch(train) [46][ 380/1320] lr: 2.0000e-04 eta: 0:26:45 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 6.9065 loss: 0.9358 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9358 2023/02/18 03:40:51 - mmengine - INFO - Epoch(train) [46][ 400/1320] lr: 2.0000e-04 eta: 0:26:39 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 7.0099 loss: 0.9004 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.9004 2023/02/18 03:40:56 - mmengine - INFO - Epoch(train) [46][ 420/1320] lr: 2.0000e-04 eta: 0:26:34 time: 0.2569 data_time: 0.0108 memory: 13708 grad_norm: 6.9860 loss: 1.0230 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0230 2023/02/18 03:41:02 - mmengine - INFO - Epoch(train) [46][ 440/1320] lr: 2.0000e-04 eta: 0:26:29 time: 0.2554 data_time: 0.0109 memory: 13708 grad_norm: 6.7955 loss: 1.0421 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0421 2023/02/18 03:41:07 - mmengine - INFO - Epoch(train) [46][ 460/1320] lr: 2.0000e-04 eta: 0:26:24 time: 0.2560 data_time: 0.0111 memory: 13708 grad_norm: 7.2416 loss: 1.0383 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0383 2023/02/18 03:41:12 - mmengine - INFO - Epoch(train) [46][ 480/1320] lr: 2.0000e-04 eta: 0:26:19 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 7.0523 loss: 1.0983 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0983 2023/02/18 03:41:17 - mmengine - INFO - Epoch(train) [46][ 500/1320] lr: 2.0000e-04 eta: 0:26:14 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 6.9892 loss: 0.8871 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.8871 2023/02/18 03:41:22 - mmengine - INFO - Epoch(train) [46][ 520/1320] lr: 2.0000e-04 eta: 0:26:09 time: 0.2565 data_time: 0.0113 memory: 13708 grad_norm: 6.6204 loss: 0.9263 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9263 2023/02/18 03:41:27 - mmengine - INFO - Epoch(train) [46][ 540/1320] lr: 2.0000e-04 eta: 0:26:03 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 7.0578 loss: 0.9921 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9921 2023/02/18 03:41:32 - mmengine - INFO - Epoch(train) [46][ 560/1320] lr: 2.0000e-04 eta: 0:25:58 time: 0.2563 data_time: 0.0112 memory: 13708 grad_norm: 7.0500 loss: 0.8352 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8352 2023/02/18 03:41:37 - mmengine - INFO - Epoch(train) [46][ 580/1320] lr: 2.0000e-04 eta: 0:25:53 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 7.0121 loss: 0.8805 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8805 2023/02/18 03:41:43 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:41:43 - mmengine - INFO - Epoch(train) [46][ 600/1320] lr: 2.0000e-04 eta: 0:25:48 time: 0.2562 data_time: 0.0115 memory: 13708 grad_norm: 7.0673 loss: 0.9072 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 0.9072 2023/02/18 03:41:48 - mmengine - INFO - Epoch(train) [46][ 620/1320] lr: 2.0000e-04 eta: 0:25:43 time: 0.2562 data_time: 0.0112 memory: 13708 grad_norm: 7.0749 loss: 0.9681 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9681 2023/02/18 03:41:53 - mmengine - INFO - Epoch(train) [46][ 640/1320] lr: 2.0000e-04 eta: 0:25:38 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 7.2189 loss: 0.9102 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9102 2023/02/18 03:41:58 - mmengine - INFO - Epoch(train) [46][ 660/1320] lr: 2.0000e-04 eta: 0:25:32 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 6.9217 loss: 0.8218 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.8218 2023/02/18 03:42:03 - mmengine - INFO - Epoch(train) [46][ 680/1320] lr: 2.0000e-04 eta: 0:25:27 time: 0.2564 data_time: 0.0108 memory: 13708 grad_norm: 6.7734 loss: 0.9726 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9726 2023/02/18 03:42:08 - mmengine - INFO - Epoch(train) [46][ 700/1320] lr: 2.0000e-04 eta: 0:25:22 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 6.9358 loss: 0.9353 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 0.9353 2023/02/18 03:42:13 - mmengine - INFO - Epoch(train) [46][ 720/1320] lr: 2.0000e-04 eta: 0:25:17 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 7.0545 loss: 0.9413 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 0.9413 2023/02/18 03:42:18 - mmengine - INFO - Epoch(train) [46][ 740/1320] lr: 2.0000e-04 eta: 0:25:12 time: 0.2567 data_time: 0.0113 memory: 13708 grad_norm: 6.8704 loss: 0.9321 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 0.9321 2023/02/18 03:42:24 - mmengine - INFO - Epoch(train) [46][ 760/1320] lr: 2.0000e-04 eta: 0:25:07 time: 0.2561 data_time: 0.0104 memory: 13708 grad_norm: 6.9570 loss: 1.0973 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0973 2023/02/18 03:42:29 - mmengine - INFO - Epoch(train) [46][ 780/1320] lr: 2.0000e-04 eta: 0:25:01 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 7.0935 loss: 1.0031 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0031 2023/02/18 03:42:34 - mmengine - INFO - Epoch(train) [46][ 800/1320] lr: 2.0000e-04 eta: 0:24:56 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 7.1039 loss: 1.0539 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0539 2023/02/18 03:42:39 - mmengine - INFO - Epoch(train) [46][ 820/1320] lr: 2.0000e-04 eta: 0:24:51 time: 0.2561 data_time: 0.0105 memory: 13708 grad_norm: 7.0830 loss: 0.9476 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9476 2023/02/18 03:42:44 - mmengine - INFO - Epoch(train) [46][ 840/1320] lr: 2.0000e-04 eta: 0:24:46 time: 0.2562 data_time: 0.0112 memory: 13708 grad_norm: 6.9869 loss: 0.9109 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9109 2023/02/18 03:42:49 - mmengine - INFO - Epoch(train) [46][ 860/1320] lr: 2.0000e-04 eta: 0:24:41 time: 0.2568 data_time: 0.0107 memory: 13708 grad_norm: 6.9590 loss: 0.9225 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9225 2023/02/18 03:42:54 - mmengine - INFO - Epoch(train) [46][ 880/1320] lr: 2.0000e-04 eta: 0:24:36 time: 0.2564 data_time: 0.0110 memory: 13708 grad_norm: 7.1378 loss: 1.0333 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0333 2023/02/18 03:42:59 - mmengine - INFO - Epoch(train) [46][ 900/1320] lr: 2.0000e-04 eta: 0:24:30 time: 0.2565 data_time: 0.0107 memory: 13708 grad_norm: 7.1305 loss: 0.9133 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9133 2023/02/18 03:43:05 - mmengine - INFO - Epoch(train) [46][ 920/1320] lr: 2.0000e-04 eta: 0:24:25 time: 0.2589 data_time: 0.0132 memory: 13708 grad_norm: 7.1540 loss: 0.8051 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.8051 2023/02/18 03:43:10 - mmengine - INFO - Epoch(train) [46][ 940/1320] lr: 2.0000e-04 eta: 0:24:20 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 6.9651 loss: 0.8504 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8504 2023/02/18 03:43:15 - mmengine - INFO - Epoch(train) [46][ 960/1320] lr: 2.0000e-04 eta: 0:24:15 time: 0.2561 data_time: 0.0105 memory: 13708 grad_norm: 6.9584 loss: 0.9769 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9769 2023/02/18 03:43:20 - mmengine - INFO - Epoch(train) [46][ 980/1320] lr: 2.0000e-04 eta: 0:24:10 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 6.8806 loss: 0.7362 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7362 2023/02/18 03:43:25 - mmengine - INFO - Epoch(train) [46][1000/1320] lr: 2.0000e-04 eta: 0:24:05 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 7.0332 loss: 0.9509 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9509 2023/02/18 03:43:30 - mmengine - INFO - Epoch(train) [46][1020/1320] lr: 2.0000e-04 eta: 0:23:59 time: 0.2564 data_time: 0.0110 memory: 13708 grad_norm: 6.9770 loss: 0.9474 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 0.9474 2023/02/18 03:43:35 - mmengine - INFO - Epoch(train) [46][1040/1320] lr: 2.0000e-04 eta: 0:23:54 time: 0.2563 data_time: 0.0104 memory: 13708 grad_norm: 6.9300 loss: 0.9881 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9881 2023/02/18 03:43:41 - mmengine - INFO - Epoch(train) [46][1060/1320] lr: 2.0000e-04 eta: 0:23:49 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 6.9933 loss: 1.0180 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0180 2023/02/18 03:43:46 - mmengine - INFO - Epoch(train) [46][1080/1320] lr: 2.0000e-04 eta: 0:23:44 time: 0.2557 data_time: 0.0108 memory: 13708 grad_norm: 6.8793 loss: 0.9214 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9214 2023/02/18 03:43:51 - mmengine - INFO - Epoch(train) [46][1100/1320] lr: 2.0000e-04 eta: 0:23:39 time: 0.2603 data_time: 0.0108 memory: 13708 grad_norm: 6.9706 loss: 0.9816 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.9816 2023/02/18 03:43:56 - mmengine - INFO - Epoch(train) [46][1120/1320] lr: 2.0000e-04 eta: 0:23:34 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 6.9499 loss: 0.9511 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9511 2023/02/18 03:44:01 - mmengine - INFO - Epoch(train) [46][1140/1320] lr: 2.0000e-04 eta: 0:23:28 time: 0.2564 data_time: 0.0106 memory: 13708 grad_norm: 7.2260 loss: 0.8960 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8960 2023/02/18 03:44:06 - mmengine - INFO - Epoch(train) [46][1160/1320] lr: 2.0000e-04 eta: 0:23:23 time: 0.2575 data_time: 0.0110 memory: 13708 grad_norm: 7.0056 loss: 0.9567 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9567 2023/02/18 03:44:11 - mmengine - INFO - Epoch(train) [46][1180/1320] lr: 2.0000e-04 eta: 0:23:18 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 7.1044 loss: 1.0382 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0382 2023/02/18 03:44:17 - mmengine - INFO - Epoch(train) [46][1200/1320] lr: 2.0000e-04 eta: 0:23:13 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 6.9519 loss: 0.8661 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8661 2023/02/18 03:44:22 - mmengine - INFO - Epoch(train) [46][1220/1320] lr: 2.0000e-04 eta: 0:23:08 time: 0.2566 data_time: 0.0114 memory: 13708 grad_norm: 6.9685 loss: 0.9258 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9258 2023/02/18 03:44:27 - mmengine - INFO - Epoch(train) [46][1240/1320] lr: 2.0000e-04 eta: 0:23:03 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 7.0161 loss: 0.9378 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9378 2023/02/18 03:44:32 - mmengine - INFO - Epoch(train) [46][1260/1320] lr: 2.0000e-04 eta: 0:22:57 time: 0.2571 data_time: 0.0112 memory: 13708 grad_norm: 7.1066 loss: 0.9319 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9319 2023/02/18 03:44:37 - mmengine - INFO - Epoch(train) [46][1280/1320] lr: 2.0000e-04 eta: 0:22:52 time: 0.2567 data_time: 0.0109 memory: 13708 grad_norm: 7.2765 loss: 0.9451 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9451 2023/02/18 03:44:42 - mmengine - INFO - Epoch(train) [46][1300/1320] lr: 2.0000e-04 eta: 0:22:47 time: 0.2559 data_time: 0.0103 memory: 13708 grad_norm: 7.0279 loss: 0.9144 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9144 2023/02/18 03:44:47 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:44:47 - mmengine - INFO - Epoch(train) [46][1320/1320] lr: 2.0000e-04 eta: 0:22:42 time: 0.2519 data_time: 0.0108 memory: 13708 grad_norm: 7.1452 loss: 0.8885 top1_acc: 0.6364 top5_acc: 0.8182 loss_cls: 0.8885 2023/02/18 03:44:50 - mmengine - INFO - Epoch(val) [46][ 20/194] eta: 0:00:22 time: 0.1286 data_time: 0.0597 memory: 1818 2023/02/18 03:44:52 - mmengine - INFO - Epoch(val) [46][ 40/194] eta: 0:00:16 time: 0.0873 data_time: 0.0182 memory: 1818 2023/02/18 03:44:53 - mmengine - INFO - Epoch(val) [46][ 60/194] eta: 0:00:13 time: 0.0860 data_time: 0.0177 memory: 1818 2023/02/18 03:44:55 - mmengine - INFO - Epoch(val) [46][ 80/194] eta: 0:00:11 time: 0.0855 data_time: 0.0175 memory: 1818 2023/02/18 03:44:57 - mmengine - INFO - Epoch(val) [46][100/194] eta: 0:00:08 time: 0.0880 data_time: 0.0189 memory: 1818 2023/02/18 03:44:58 - mmengine - INFO - Epoch(val) [46][120/194] eta: 0:00:06 time: 0.0852 data_time: 0.0167 memory: 1818 2023/02/18 03:45:00 - mmengine - INFO - Epoch(val) [46][140/194] eta: 0:00:05 time: 0.0892 data_time: 0.0204 memory: 1818 2023/02/18 03:45:02 - mmengine - INFO - Epoch(val) [46][160/194] eta: 0:00:03 time: 0.0844 data_time: 0.0154 memory: 1818 2023/02/18 03:45:04 - mmengine - INFO - Epoch(val) [46][180/194] eta: 0:00:01 time: 0.0857 data_time: 0.0153 memory: 1818 2023/02/18 03:45:06 - mmengine - INFO - Epoch(val) [46][194/194] acc/top1: 0.5963 acc/top5: 0.8589 acc/mean1: 0.5318 2023/02/18 03:45:06 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_37.pth is removed 2023/02/18 03:45:07 - mmengine - INFO - The best checkpoint with 0.5963 acc/top1 at 46 epoch is saved to best_acc/top1_epoch_46.pth. 2023/02/18 03:45:13 - mmengine - INFO - Epoch(train) [47][ 20/1320] lr: 2.0000e-04 eta: 0:22:37 time: 0.2935 data_time: 0.0410 memory: 13708 grad_norm: 6.9840 loss: 0.9587 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9587 2023/02/18 03:45:18 - mmengine - INFO - Epoch(train) [47][ 40/1320] lr: 2.0000e-04 eta: 0:22:32 time: 0.2560 data_time: 0.0103 memory: 13708 grad_norm: 7.0073 loss: 1.0287 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0287 2023/02/18 03:45:23 - mmengine - INFO - Epoch(train) [47][ 60/1320] lr: 2.0000e-04 eta: 0:22:27 time: 0.2559 data_time: 0.0109 memory: 13708 grad_norm: 7.1633 loss: 1.0185 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0185 2023/02/18 03:45:28 - mmengine - INFO - Epoch(train) [47][ 80/1320] lr: 2.0000e-04 eta: 0:22:21 time: 0.2556 data_time: 0.0106 memory: 13708 grad_norm: 6.7210 loss: 0.9570 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.9570 2023/02/18 03:45:33 - mmengine - INFO - Epoch(train) [47][ 100/1320] lr: 2.0000e-04 eta: 0:22:16 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 6.9736 loss: 0.8889 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8889 2023/02/18 03:45:38 - mmengine - INFO - Epoch(train) [47][ 120/1320] lr: 2.0000e-04 eta: 0:22:11 time: 0.2556 data_time: 0.0108 memory: 13708 grad_norm: 6.9539 loss: 0.6987 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6987 2023/02/18 03:45:43 - mmengine - INFO - Epoch(train) [47][ 140/1320] lr: 2.0000e-04 eta: 0:22:06 time: 0.2580 data_time: 0.0129 memory: 13708 grad_norm: 6.9895 loss: 0.7900 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.7900 2023/02/18 03:45:49 - mmengine - INFO - Epoch(train) [47][ 160/1320] lr: 2.0000e-04 eta: 0:22:01 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 7.1341 loss: 0.9049 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9049 2023/02/18 03:45:54 - mmengine - INFO - Epoch(train) [47][ 180/1320] lr: 2.0000e-04 eta: 0:21:56 time: 0.2573 data_time: 0.0110 memory: 13708 grad_norm: 7.0271 loss: 1.0337 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0337 2023/02/18 03:45:59 - mmengine - INFO - Epoch(train) [47][ 200/1320] lr: 2.0000e-04 eta: 0:21:50 time: 0.2557 data_time: 0.0105 memory: 13708 grad_norm: 6.9908 loss: 0.8972 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8972 2023/02/18 03:46:04 - mmengine - INFO - Epoch(train) [47][ 220/1320] lr: 2.0000e-04 eta: 0:21:45 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 7.0536 loss: 0.8694 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8694 2023/02/18 03:46:09 - mmengine - INFO - Epoch(train) [47][ 240/1320] lr: 2.0000e-04 eta: 0:21:40 time: 0.2563 data_time: 0.0106 memory: 13708 grad_norm: 6.8510 loss: 1.0157 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0157 2023/02/18 03:46:14 - mmengine - INFO - Epoch(train) [47][ 260/1320] lr: 2.0000e-04 eta: 0:21:35 time: 0.2557 data_time: 0.0109 memory: 13708 grad_norm: 6.9675 loss: 0.8443 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8443 2023/02/18 03:46:19 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:46:19 - mmengine - INFO - Epoch(train) [47][ 280/1320] lr: 2.0000e-04 eta: 0:21:30 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 6.9400 loss: 0.8689 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8689 2023/02/18 03:46:24 - mmengine - INFO - Epoch(train) [47][ 300/1320] lr: 2.0000e-04 eta: 0:21:25 time: 0.2561 data_time: 0.0105 memory: 13708 grad_norm: 7.2191 loss: 0.9693 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9693 2023/02/18 03:46:30 - mmengine - INFO - Epoch(train) [47][ 320/1320] lr: 2.0000e-04 eta: 0:21:19 time: 0.2562 data_time: 0.0112 memory: 13708 grad_norm: 6.9304 loss: 0.8552 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.8552 2023/02/18 03:46:35 - mmengine - INFO - Epoch(train) [47][ 340/1320] lr: 2.0000e-04 eta: 0:21:14 time: 0.2556 data_time: 0.0105 memory: 13708 grad_norm: 7.0665 loss: 1.0103 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.0103 2023/02/18 03:46:40 - mmengine - INFO - Epoch(train) [47][ 360/1320] lr: 2.0000e-04 eta: 0:21:09 time: 0.2563 data_time: 0.0106 memory: 13708 grad_norm: 7.1137 loss: 0.9478 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9478 2023/02/18 03:46:45 - mmengine - INFO - Epoch(train) [47][ 380/1320] lr: 2.0000e-04 eta: 0:21:04 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 7.1897 loss: 0.9880 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.9880 2023/02/18 03:46:50 - mmengine - INFO - Epoch(train) [47][ 400/1320] lr: 2.0000e-04 eta: 0:20:59 time: 0.2566 data_time: 0.0104 memory: 13708 grad_norm: 7.1697 loss: 0.8382 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8382 2023/02/18 03:46:55 - mmengine - INFO - Epoch(train) [47][ 420/1320] lr: 2.0000e-04 eta: 0:20:54 time: 0.2565 data_time: 0.0112 memory: 13708 grad_norm: 7.3393 loss: 0.8280 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8280 2023/02/18 03:47:00 - mmengine - INFO - Epoch(train) [47][ 440/1320] lr: 2.0000e-04 eta: 0:20:48 time: 0.2561 data_time: 0.0113 memory: 13708 grad_norm: 6.8705 loss: 0.8815 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8815 2023/02/18 03:47:05 - mmengine - INFO - Epoch(train) [47][ 460/1320] lr: 2.0000e-04 eta: 0:20:43 time: 0.2570 data_time: 0.0113 memory: 13708 grad_norm: 7.1114 loss: 0.9442 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9442 2023/02/18 03:47:11 - mmengine - INFO - Epoch(train) [47][ 480/1320] lr: 2.0000e-04 eta: 0:20:38 time: 0.2567 data_time: 0.0111 memory: 13708 grad_norm: 6.9398 loss: 0.8148 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8148 2023/02/18 03:47:16 - mmengine - INFO - Epoch(train) [47][ 500/1320] lr: 2.0000e-04 eta: 0:20:33 time: 0.2570 data_time: 0.0108 memory: 13708 grad_norm: 7.1491 loss: 1.0162 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 1.0162 2023/02/18 03:47:21 - mmengine - INFO - Epoch(train) [47][ 520/1320] lr: 2.0000e-04 eta: 0:20:28 time: 0.2572 data_time: 0.0107 memory: 13708 grad_norm: 6.9402 loss: 0.8718 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8718 2023/02/18 03:47:26 - mmengine - INFO - Epoch(train) [47][ 540/1320] lr: 2.0000e-04 eta: 0:20:23 time: 0.2564 data_time: 0.0112 memory: 13708 grad_norm: 7.1285 loss: 0.7440 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.7440 2023/02/18 03:47:31 - mmengine - INFO - Epoch(train) [47][ 560/1320] lr: 2.0000e-04 eta: 0:20:17 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 7.1031 loss: 0.7609 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7609 2023/02/18 03:47:36 - mmengine - INFO - Epoch(train) [47][ 580/1320] lr: 2.0000e-04 eta: 0:20:12 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 6.8868 loss: 0.9100 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9100 2023/02/18 03:47:41 - mmengine - INFO - Epoch(train) [47][ 600/1320] lr: 2.0000e-04 eta: 0:20:07 time: 0.2561 data_time: 0.0112 memory: 13708 grad_norm: 7.2345 loss: 1.0478 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.0478 2023/02/18 03:47:47 - mmengine - INFO - Epoch(train) [47][ 620/1320] lr: 2.0000e-04 eta: 0:20:02 time: 0.2566 data_time: 0.0109 memory: 13708 grad_norm: 6.9293 loss: 0.9186 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9186 2023/02/18 03:47:52 - mmengine - INFO - Epoch(train) [47][ 640/1320] lr: 2.0000e-04 eta: 0:19:57 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 6.7656 loss: 0.8780 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8780 2023/02/18 03:47:57 - mmengine - INFO - Epoch(train) [47][ 660/1320] lr: 2.0000e-04 eta: 0:19:52 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 7.1460 loss: 1.1707 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1707 2023/02/18 03:48:02 - mmengine - INFO - Epoch(train) [47][ 680/1320] lr: 2.0000e-04 eta: 0:19:46 time: 0.2562 data_time: 0.0103 memory: 13708 grad_norm: 7.1236 loss: 0.9779 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9779 2023/02/18 03:48:07 - mmengine - INFO - Epoch(train) [47][ 700/1320] lr: 2.0000e-04 eta: 0:19:41 time: 0.2566 data_time: 0.0109 memory: 13708 grad_norm: 7.1182 loss: 0.9552 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9552 2023/02/18 03:48:12 - mmengine - INFO - Epoch(train) [47][ 720/1320] lr: 2.0000e-04 eta: 0:19:36 time: 0.2559 data_time: 0.0106 memory: 13708 grad_norm: 6.8627 loss: 0.7653 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.7653 2023/02/18 03:48:17 - mmengine - INFO - Epoch(train) [47][ 740/1320] lr: 2.0000e-04 eta: 0:19:31 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 7.0449 loss: 0.7898 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7898 2023/02/18 03:48:22 - mmengine - INFO - Epoch(train) [47][ 760/1320] lr: 2.0000e-04 eta: 0:19:26 time: 0.2561 data_time: 0.0108 memory: 13708 grad_norm: 7.1480 loss: 0.9545 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9545 2023/02/18 03:48:28 - mmengine - INFO - Epoch(train) [47][ 780/1320] lr: 2.0000e-04 eta: 0:19:21 time: 0.2563 data_time: 0.0107 memory: 13708 grad_norm: 7.0724 loss: 0.9753 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9753 2023/02/18 03:48:33 - mmengine - INFO - Epoch(train) [47][ 800/1320] lr: 2.0000e-04 eta: 0:19:15 time: 0.2582 data_time: 0.0132 memory: 13708 grad_norm: 6.9657 loss: 0.9777 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.9777 2023/02/18 03:48:38 - mmengine - INFO - Epoch(train) [47][ 820/1320] lr: 2.0000e-04 eta: 0:19:10 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 6.8827 loss: 0.8816 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8816 2023/02/18 03:48:43 - mmengine - INFO - Epoch(train) [47][ 840/1320] lr: 2.0000e-04 eta: 0:19:05 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 7.1253 loss: 0.9136 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9136 2023/02/18 03:48:48 - mmengine - INFO - Epoch(train) [47][ 860/1320] lr: 2.0000e-04 eta: 0:19:00 time: 0.2569 data_time: 0.0112 memory: 13708 grad_norm: 7.0912 loss: 0.8794 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.8794 2023/02/18 03:48:53 - mmengine - INFO - Epoch(train) [47][ 880/1320] lr: 2.0000e-04 eta: 0:18:55 time: 0.2559 data_time: 0.0108 memory: 13708 grad_norm: 7.0125 loss: 0.8055 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8055 2023/02/18 03:48:58 - mmengine - INFO - Epoch(train) [47][ 900/1320] lr: 2.0000e-04 eta: 0:18:50 time: 0.2568 data_time: 0.0112 memory: 13708 grad_norm: 7.0662 loss: 0.8437 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8437 2023/02/18 03:49:04 - mmengine - INFO - Epoch(train) [47][ 920/1320] lr: 2.0000e-04 eta: 0:18:44 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 7.1881 loss: 0.8327 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8327 2023/02/18 03:49:09 - mmengine - INFO - Epoch(train) [47][ 940/1320] lr: 2.0000e-04 eta: 0:18:39 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 7.1813 loss: 1.0193 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0193 2023/02/18 03:49:14 - mmengine - INFO - Epoch(train) [47][ 960/1320] lr: 2.0000e-04 eta: 0:18:34 time: 0.2573 data_time: 0.0119 memory: 13708 grad_norm: 7.1417 loss: 1.0169 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0169 2023/02/18 03:49:19 - mmengine - INFO - Epoch(train) [47][ 980/1320] lr: 2.0000e-04 eta: 0:18:29 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 7.0745 loss: 0.9429 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9429 2023/02/18 03:49:24 - mmengine - INFO - Epoch(train) [47][1000/1320] lr: 2.0000e-04 eta: 0:18:24 time: 0.2564 data_time: 0.0105 memory: 13708 grad_norm: 7.0455 loss: 1.0023 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0023 2023/02/18 03:49:29 - mmengine - INFO - Epoch(train) [47][1020/1320] lr: 2.0000e-04 eta: 0:18:19 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 7.3369 loss: 0.9673 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9673 2023/02/18 03:49:34 - mmengine - INFO - Epoch(train) [47][1040/1320] lr: 2.0000e-04 eta: 0:18:14 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 7.1238 loss: 0.9587 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9587 2023/02/18 03:49:39 - mmengine - INFO - Epoch(train) [47][1060/1320] lr: 2.0000e-04 eta: 0:18:08 time: 0.2567 data_time: 0.0111 memory: 13708 grad_norm: 7.1903 loss: 1.1031 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1031 2023/02/18 03:49:45 - mmengine - INFO - Epoch(train) [47][1080/1320] lr: 2.0000e-04 eta: 0:18:03 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 7.0019 loss: 0.8089 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8089 2023/02/18 03:49:50 - mmengine - INFO - Epoch(train) [47][1100/1320] lr: 2.0000e-04 eta: 0:17:58 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 7.2009 loss: 0.9869 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 0.9869 2023/02/18 03:49:55 - mmengine - INFO - Epoch(train) [47][1120/1320] lr: 2.0000e-04 eta: 0:17:53 time: 0.2565 data_time: 0.0116 memory: 13708 grad_norm: 7.0991 loss: 0.9255 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 0.9255 2023/02/18 03:50:00 - mmengine - INFO - Epoch(train) [47][1140/1320] lr: 2.0000e-04 eta: 0:17:48 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 7.3508 loss: 1.0687 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.0687 2023/02/18 03:50:05 - mmengine - INFO - Epoch(train) [47][1160/1320] lr: 2.0000e-04 eta: 0:17:43 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 7.2303 loss: 0.8405 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.8405 2023/02/18 03:50:10 - mmengine - INFO - Epoch(train) [47][1180/1320] lr: 2.0000e-04 eta: 0:17:37 time: 0.2573 data_time: 0.0123 memory: 13708 grad_norm: 7.1479 loss: 0.9522 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9522 2023/02/18 03:50:15 - mmengine - INFO - Epoch(train) [47][1200/1320] lr: 2.0000e-04 eta: 0:17:32 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 7.2395 loss: 0.9197 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9197 2023/02/18 03:50:21 - mmengine - INFO - Epoch(train) [47][1220/1320] lr: 2.0000e-04 eta: 0:17:27 time: 0.2566 data_time: 0.0108 memory: 13708 grad_norm: 6.9868 loss: 0.9613 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9613 2023/02/18 03:50:26 - mmengine - INFO - Epoch(train) [47][1240/1320] lr: 2.0000e-04 eta: 0:17:22 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 7.0635 loss: 0.8680 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8680 2023/02/18 03:50:31 - mmengine - INFO - Epoch(train) [47][1260/1320] lr: 2.0000e-04 eta: 0:17:17 time: 0.2555 data_time: 0.0103 memory: 13708 grad_norm: 7.1313 loss: 0.9700 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 0.9700 2023/02/18 03:50:36 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:50:36 - mmengine - INFO - Epoch(train) [47][1280/1320] lr: 2.0000e-04 eta: 0:17:12 time: 0.2568 data_time: 0.0112 memory: 13708 grad_norm: 6.9535 loss: 0.8469 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8469 2023/02/18 03:50:41 - mmengine - INFO - Epoch(train) [47][1300/1320] lr: 2.0000e-04 eta: 0:17:06 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 7.1764 loss: 0.9960 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9960 2023/02/18 03:50:46 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:50:46 - mmengine - INFO - Epoch(train) [47][1320/1320] lr: 2.0000e-04 eta: 0:17:01 time: 0.2517 data_time: 0.0106 memory: 13708 grad_norm: 7.1549 loss: 1.0053 top1_acc: 0.8182 top5_acc: 0.8182 loss_cls: 1.0053 2023/02/18 03:50:49 - mmengine - INFO - Epoch(val) [47][ 20/194] eta: 0:00:22 time: 0.1303 data_time: 0.0615 memory: 1818 2023/02/18 03:50:50 - mmengine - INFO - Epoch(val) [47][ 40/194] eta: 0:00:16 time: 0.0851 data_time: 0.0168 memory: 1818 2023/02/18 03:50:52 - mmengine - INFO - Epoch(val) [47][ 60/194] eta: 0:00:13 time: 0.0882 data_time: 0.0206 memory: 1818 2023/02/18 03:50:54 - mmengine - INFO - Epoch(val) [47][ 80/194] eta: 0:00:11 time: 0.0857 data_time: 0.0176 memory: 1818 2023/02/18 03:50:56 - mmengine - INFO - Epoch(val) [47][100/194] eta: 0:00:09 time: 0.0904 data_time: 0.0216 memory: 1818 2023/02/18 03:50:57 - mmengine - INFO - Epoch(val) [47][120/194] eta: 0:00:07 time: 0.0899 data_time: 0.0215 memory: 1818 2023/02/18 03:50:59 - mmengine - INFO - Epoch(val) [47][140/194] eta: 0:00:05 time: 0.0876 data_time: 0.0186 memory: 1818 2023/02/18 03:51:01 - mmengine - INFO - Epoch(val) [47][160/194] eta: 0:00:03 time: 0.0832 data_time: 0.0149 memory: 1818 2023/02/18 03:51:03 - mmengine - INFO - Epoch(val) [47][180/194] eta: 0:00:01 time: 0.0859 data_time: 0.0171 memory: 1818 2023/02/18 03:51:05 - mmengine - INFO - Epoch(val) [47][194/194] acc/top1: 0.5961 acc/top5: 0.8586 acc/mean1: 0.5342 2023/02/18 03:51:11 - mmengine - INFO - Epoch(train) [48][ 20/1320] lr: 2.0000e-04 eta: 0:16:56 time: 0.2987 data_time: 0.0435 memory: 13708 grad_norm: 7.2275 loss: 1.0330 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0330 2023/02/18 03:51:16 - mmengine - INFO - Epoch(train) [48][ 40/1320] lr: 2.0000e-04 eta: 0:16:51 time: 0.2567 data_time: 0.0108 memory: 13708 grad_norm: 7.1221 loss: 0.9123 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9123 2023/02/18 03:51:21 - mmengine - INFO - Epoch(train) [48][ 60/1320] lr: 2.0000e-04 eta: 0:16:46 time: 0.2561 data_time: 0.0113 memory: 13708 grad_norm: 6.9915 loss: 0.9563 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9563 2023/02/18 03:51:26 - mmengine - INFO - Epoch(train) [48][ 80/1320] lr: 2.0000e-04 eta: 0:16:41 time: 0.2566 data_time: 0.0110 memory: 13708 grad_norm: 7.2266 loss: 0.9252 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9252 2023/02/18 03:51:31 - mmengine - INFO - Epoch(train) [48][ 100/1320] lr: 2.0000e-04 eta: 0:16:35 time: 0.2560 data_time: 0.0103 memory: 13708 grad_norm: 7.1446 loss: 0.9905 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9905 2023/02/18 03:51:36 - mmengine - INFO - Epoch(train) [48][ 120/1320] lr: 2.0000e-04 eta: 0:16:30 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 7.1260 loss: 0.9072 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9072 2023/02/18 03:51:41 - mmengine - INFO - Epoch(train) [48][ 140/1320] lr: 2.0000e-04 eta: 0:16:25 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 6.8528 loss: 0.8887 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8887 2023/02/18 03:51:46 - mmengine - INFO - Epoch(train) [48][ 160/1320] lr: 2.0000e-04 eta: 0:16:20 time: 0.2562 data_time: 0.0110 memory: 13708 grad_norm: 7.1476 loss: 0.9583 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9583 2023/02/18 03:51:52 - mmengine - INFO - Epoch(train) [48][ 180/1320] lr: 2.0000e-04 eta: 0:16:15 time: 0.2569 data_time: 0.0117 memory: 13708 grad_norm: 7.0934 loss: 0.9229 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9229 2023/02/18 03:51:57 - mmengine - INFO - Epoch(train) [48][ 200/1320] lr: 2.0000e-04 eta: 0:16:10 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 7.0264 loss: 0.9188 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9188 2023/02/18 03:52:02 - mmengine - INFO - Epoch(train) [48][ 220/1320] lr: 2.0000e-04 eta: 0:16:04 time: 0.2572 data_time: 0.0114 memory: 13708 grad_norm: 7.4148 loss: 0.9711 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9711 2023/02/18 03:52:07 - mmengine - INFO - Epoch(train) [48][ 240/1320] lr: 2.0000e-04 eta: 0:15:59 time: 0.2569 data_time: 0.0110 memory: 13708 grad_norm: 7.1265 loss: 0.9086 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9086 2023/02/18 03:52:12 - mmengine - INFO - Epoch(train) [48][ 260/1320] lr: 2.0000e-04 eta: 0:15:54 time: 0.2564 data_time: 0.0107 memory: 13708 grad_norm: 7.1852 loss: 0.9683 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9683 2023/02/18 03:52:17 - mmengine - INFO - Epoch(train) [48][ 280/1320] lr: 2.0000e-04 eta: 0:15:49 time: 0.2574 data_time: 0.0112 memory: 13708 grad_norm: 7.1173 loss: 0.8035 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8035 2023/02/18 03:52:22 - mmengine - INFO - Epoch(train) [48][ 300/1320] lr: 2.0000e-04 eta: 0:15:44 time: 0.2565 data_time: 0.0104 memory: 13708 grad_norm: 7.3300 loss: 1.0326 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0326 2023/02/18 03:52:28 - mmengine - INFO - Epoch(train) [48][ 320/1320] lr: 2.0000e-04 eta: 0:15:39 time: 0.2564 data_time: 0.0112 memory: 13708 grad_norm: 7.1102 loss: 0.9880 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9880 2023/02/18 03:52:33 - mmengine - INFO - Epoch(train) [48][ 340/1320] lr: 2.0000e-04 eta: 0:15:34 time: 0.2565 data_time: 0.0107 memory: 13708 grad_norm: 7.2316 loss: 0.9499 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9499 2023/02/18 03:52:38 - mmengine - INFO - Epoch(train) [48][ 360/1320] lr: 2.0000e-04 eta: 0:15:28 time: 0.2564 data_time: 0.0110 memory: 13708 grad_norm: 7.1437 loss: 0.9548 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9548 2023/02/18 03:52:43 - mmengine - INFO - Epoch(train) [48][ 380/1320] lr: 2.0000e-04 eta: 0:15:23 time: 0.2564 data_time: 0.0106 memory: 13708 grad_norm: 7.3308 loss: 0.8949 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8949 2023/02/18 03:52:48 - mmengine - INFO - Epoch(train) [48][ 400/1320] lr: 2.0000e-04 eta: 0:15:18 time: 0.2572 data_time: 0.0112 memory: 13708 grad_norm: 7.2831 loss: 0.9076 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9076 2023/02/18 03:52:53 - mmengine - INFO - Epoch(train) [48][ 420/1320] lr: 2.0000e-04 eta: 0:15:13 time: 0.2575 data_time: 0.0106 memory: 13708 grad_norm: 7.1176 loss: 0.8132 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8132 2023/02/18 03:52:58 - mmengine - INFO - Epoch(train) [48][ 440/1320] lr: 2.0000e-04 eta: 0:15:08 time: 0.2573 data_time: 0.0110 memory: 13708 grad_norm: 7.3138 loss: 0.8160 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8160 2023/02/18 03:53:04 - mmengine - INFO - Epoch(train) [48][ 460/1320] lr: 2.0000e-04 eta: 0:15:03 time: 0.2566 data_time: 0.0113 memory: 13708 grad_norm: 7.1727 loss: 0.9684 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9684 2023/02/18 03:53:09 - mmengine - INFO - Epoch(train) [48][ 480/1320] lr: 2.0000e-04 eta: 0:14:57 time: 0.2566 data_time: 0.0107 memory: 13708 grad_norm: 6.9885 loss: 0.9025 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9025 2023/02/18 03:53:14 - mmengine - INFO - Epoch(train) [48][ 500/1320] lr: 2.0000e-04 eta: 0:14:52 time: 0.2570 data_time: 0.0117 memory: 13708 grad_norm: 7.0928 loss: 0.9182 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9182 2023/02/18 03:53:19 - mmengine - INFO - Epoch(train) [48][ 520/1320] lr: 2.0000e-04 eta: 0:14:47 time: 0.2574 data_time: 0.0120 memory: 13708 grad_norm: 6.9912 loss: 0.9355 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9355 2023/02/18 03:53:24 - mmengine - INFO - Epoch(train) [48][ 540/1320] lr: 2.0000e-04 eta: 0:14:42 time: 0.2565 data_time: 0.0111 memory: 13708 grad_norm: 7.2012 loss: 0.9539 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9539 2023/02/18 03:53:29 - mmengine - INFO - Epoch(train) [48][ 560/1320] lr: 2.0000e-04 eta: 0:14:37 time: 0.2567 data_time: 0.0110 memory: 13708 grad_norm: 7.1420 loss: 0.8623 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8623 2023/02/18 03:53:34 - mmengine - INFO - Epoch(train) [48][ 580/1320] lr: 2.0000e-04 eta: 0:14:32 time: 0.2560 data_time: 0.0107 memory: 13708 grad_norm: 7.0121 loss: 0.7532 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7532 2023/02/18 03:53:40 - mmengine - INFO - Epoch(train) [48][ 600/1320] lr: 2.0000e-04 eta: 0:14:26 time: 0.2566 data_time: 0.0114 memory: 13708 grad_norm: 7.1736 loss: 1.0514 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0514 2023/02/18 03:53:45 - mmengine - INFO - Epoch(train) [48][ 620/1320] lr: 2.0000e-04 eta: 0:14:21 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 7.2971 loss: 0.9396 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9396 2023/02/18 03:53:50 - mmengine - INFO - Epoch(train) [48][ 640/1320] lr: 2.0000e-04 eta: 0:14:16 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 7.0546 loss: 0.9274 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9274 2023/02/18 03:53:55 - mmengine - INFO - Epoch(train) [48][ 660/1320] lr: 2.0000e-04 eta: 0:14:11 time: 0.2569 data_time: 0.0107 memory: 13708 grad_norm: 7.0618 loss: 1.0116 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0116 2023/02/18 03:54:00 - mmengine - INFO - Epoch(train) [48][ 680/1320] lr: 2.0000e-04 eta: 0:14:06 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 7.0921 loss: 0.8536 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8536 2023/02/18 03:54:05 - mmengine - INFO - Epoch(train) [48][ 700/1320] lr: 2.0000e-04 eta: 0:14:01 time: 0.2563 data_time: 0.0109 memory: 13708 grad_norm: 7.2298 loss: 0.8112 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8112 2023/02/18 03:54:10 - mmengine - INFO - Epoch(train) [48][ 720/1320] lr: 2.0000e-04 eta: 0:13:55 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 6.9180 loss: 1.0131 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0131 2023/02/18 03:54:15 - mmengine - INFO - Epoch(train) [48][ 740/1320] lr: 2.0000e-04 eta: 0:13:50 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 7.1250 loss: 0.8277 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8277 2023/02/18 03:54:21 - mmengine - INFO - Epoch(train) [48][ 760/1320] lr: 2.0000e-04 eta: 0:13:45 time: 0.2557 data_time: 0.0106 memory: 13708 grad_norm: 7.1028 loss: 0.9126 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9126 2023/02/18 03:54:26 - mmengine - INFO - Epoch(train) [48][ 780/1320] lr: 2.0000e-04 eta: 0:13:40 time: 0.2559 data_time: 0.0107 memory: 13708 grad_norm: 7.2703 loss: 0.8753 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 0.8753 2023/02/18 03:54:31 - mmengine - INFO - Epoch(train) [48][ 800/1320] lr: 2.0000e-04 eta: 0:13:35 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 6.9225 loss: 0.8913 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8913 2023/02/18 03:54:36 - mmengine - INFO - Epoch(train) [48][ 820/1320] lr: 2.0000e-04 eta: 0:13:30 time: 0.2584 data_time: 0.0128 memory: 13708 grad_norm: 7.2774 loss: 0.8953 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8953 2023/02/18 03:54:41 - mmengine - INFO - Epoch(train) [48][ 840/1320] lr: 2.0000e-04 eta: 0:13:24 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 7.1545 loss: 0.9602 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9602 2023/02/18 03:54:46 - mmengine - INFO - Epoch(train) [48][ 860/1320] lr: 2.0000e-04 eta: 0:13:19 time: 0.2584 data_time: 0.0126 memory: 13708 grad_norm: 7.1011 loss: 1.0845 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0845 2023/02/18 03:54:51 - mmengine - INFO - Epoch(train) [48][ 880/1320] lr: 2.0000e-04 eta: 0:13:14 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 6.9707 loss: 0.9121 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9121 2023/02/18 03:54:57 - mmengine - INFO - Epoch(train) [48][ 900/1320] lr: 2.0000e-04 eta: 0:13:09 time: 0.2558 data_time: 0.0104 memory: 13708 grad_norm: 7.2735 loss: 0.8623 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 0.8623 2023/02/18 03:55:02 - mmengine - INFO - Epoch(train) [48][ 920/1320] lr: 2.0000e-04 eta: 0:13:04 time: 0.2572 data_time: 0.0113 memory: 13708 grad_norm: 7.2965 loss: 0.9929 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9929 2023/02/18 03:55:07 - mmengine - INFO - Epoch(train) [48][ 940/1320] lr: 2.0000e-04 eta: 0:12:59 time: 0.2576 data_time: 0.0109 memory: 13708 grad_norm: 7.4348 loss: 0.8523 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.8523 2023/02/18 03:55:12 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:55:12 - mmengine - INFO - Epoch(train) [48][ 960/1320] lr: 2.0000e-04 eta: 0:12:54 time: 0.2564 data_time: 0.0107 memory: 13708 grad_norm: 7.2643 loss: 0.9497 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9497 2023/02/18 03:55:17 - mmengine - INFO - Epoch(train) [48][ 980/1320] lr: 2.0000e-04 eta: 0:12:48 time: 0.2568 data_time: 0.0114 memory: 13708 grad_norm: 7.3647 loss: 0.8600 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8600 2023/02/18 03:55:22 - mmengine - INFO - Epoch(train) [48][1000/1320] lr: 2.0000e-04 eta: 0:12:43 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 7.2823 loss: 0.7920 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7920 2023/02/18 03:55:27 - mmengine - INFO - Epoch(train) [48][1020/1320] lr: 2.0000e-04 eta: 0:12:38 time: 0.2567 data_time: 0.0110 memory: 13708 grad_norm: 7.1753 loss: 1.0452 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0452 2023/02/18 03:55:33 - mmengine - INFO - Epoch(train) [48][1040/1320] lr: 2.0000e-04 eta: 0:12:33 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 7.0533 loss: 0.9006 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9006 2023/02/18 03:55:38 - mmengine - INFO - Epoch(train) [48][1060/1320] lr: 2.0000e-04 eta: 0:12:28 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 7.4022 loss: 0.9726 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9726 2023/02/18 03:55:43 - mmengine - INFO - Epoch(train) [48][1080/1320] lr: 2.0000e-04 eta: 0:12:23 time: 0.2589 data_time: 0.0135 memory: 13708 grad_norm: 7.3950 loss: 0.9418 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9418 2023/02/18 03:55:48 - mmengine - INFO - Epoch(train) [48][1100/1320] lr: 2.0000e-04 eta: 0:12:17 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 7.1456 loss: 0.9185 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9185 2023/02/18 03:55:53 - mmengine - INFO - Epoch(train) [48][1120/1320] lr: 2.0000e-04 eta: 0:12:12 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 7.0955 loss: 1.0232 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0232 2023/02/18 03:55:58 - mmengine - INFO - Epoch(train) [48][1140/1320] lr: 2.0000e-04 eta: 0:12:07 time: 0.2563 data_time: 0.0107 memory: 13708 grad_norm: 7.1130 loss: 0.7899 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.7899 2023/02/18 03:56:03 - mmengine - INFO - Epoch(train) [48][1160/1320] lr: 2.0000e-04 eta: 0:12:02 time: 0.2570 data_time: 0.0118 memory: 13708 grad_norm: 6.9835 loss: 0.8977 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8977 2023/02/18 03:56:09 - mmengine - INFO - Epoch(train) [48][1180/1320] lr: 2.0000e-04 eta: 0:11:57 time: 0.2566 data_time: 0.0110 memory: 13708 grad_norm: 6.9954 loss: 0.9577 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9577 2023/02/18 03:56:14 - mmengine - INFO - Epoch(train) [48][1200/1320] lr: 2.0000e-04 eta: 0:11:52 time: 0.2565 data_time: 0.0110 memory: 13708 grad_norm: 7.2341 loss: 1.1038 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1038 2023/02/18 03:56:19 - mmengine - INFO - Epoch(train) [48][1220/1320] lr: 2.0000e-04 eta: 0:11:46 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 7.3176 loss: 0.9785 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9785 2023/02/18 03:56:24 - mmengine - INFO - Epoch(train) [48][1240/1320] lr: 2.0000e-04 eta: 0:11:41 time: 0.2559 data_time: 0.0111 memory: 13708 grad_norm: 7.0519 loss: 0.8840 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8840 2023/02/18 03:56:29 - mmengine - INFO - Epoch(train) [48][1260/1320] lr: 2.0000e-04 eta: 0:11:36 time: 0.2566 data_time: 0.0114 memory: 13708 grad_norm: 7.1977 loss: 1.0092 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0092 2023/02/18 03:56:34 - mmengine - INFO - Epoch(train) [48][1280/1320] lr: 2.0000e-04 eta: 0:11:31 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 6.8868 loss: 0.8678 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.8678 2023/02/18 03:56:39 - mmengine - INFO - Epoch(train) [48][1300/1320] lr: 2.0000e-04 eta: 0:11:26 time: 0.2569 data_time: 0.0111 memory: 13708 grad_norm: 7.1246 loss: 0.9937 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9937 2023/02/18 03:56:44 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:56:44 - mmengine - INFO - Epoch(train) [48][1320/1320] lr: 2.0000e-04 eta: 0:11:21 time: 0.2514 data_time: 0.0104 memory: 13708 grad_norm: 7.6244 loss: 0.9899 top1_acc: 0.6364 top5_acc: 0.9091 loss_cls: 0.9899 2023/02/18 03:56:44 - mmengine - INFO - Saving checkpoint at 48 epochs 2023/02/18 03:56:48 - mmengine - INFO - Epoch(val) [48][ 20/194] eta: 0:00:22 time: 0.1314 data_time: 0.0623 memory: 1818 2023/02/18 03:56:50 - mmengine - INFO - Epoch(val) [48][ 40/194] eta: 0:00:16 time: 0.0869 data_time: 0.0187 memory: 1818 2023/02/18 03:56:52 - mmengine - INFO - Epoch(val) [48][ 60/194] eta: 0:00:13 time: 0.0884 data_time: 0.0200 memory: 1818 2023/02/18 03:56:53 - mmengine - INFO - Epoch(val) [48][ 80/194] eta: 0:00:11 time: 0.0866 data_time: 0.0183 memory: 1818 2023/02/18 03:56:55 - mmengine - INFO - Epoch(val) [48][100/194] eta: 0:00:09 time: 0.0933 data_time: 0.0233 memory: 1818 2023/02/18 03:56:57 - mmengine - INFO - Epoch(val) [48][120/194] eta: 0:00:07 time: 0.0860 data_time: 0.0171 memory: 1818 2023/02/18 03:56:59 - mmengine - INFO - Epoch(val) [48][140/194] eta: 0:00:05 time: 0.0912 data_time: 0.0229 memory: 1818 2023/02/18 03:57:00 - mmengine - INFO - Epoch(val) [48][160/194] eta: 0:00:03 time: 0.0840 data_time: 0.0154 memory: 1818 2023/02/18 03:57:02 - mmengine - INFO - Epoch(val) [48][180/194] eta: 0:00:01 time: 0.0795 data_time: 0.0136 memory: 1818 2023/02/18 03:57:04 - mmengine - INFO - Epoch(val) [48][194/194] acc/top1: 0.5966 acc/top5: 0.8602 acc/mean1: 0.5336 2023/02/18 03:57:04 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_46.pth is removed 2023/02/18 03:57:05 - mmengine - INFO - The best checkpoint with 0.5966 acc/top1 at 48 epoch is saved to best_acc/top1_epoch_48.pth. 2023/02/18 03:57:11 - mmengine - INFO - Epoch(train) [49][ 20/1320] lr: 2.0000e-04 eta: 0:11:15 time: 0.2952 data_time: 0.0406 memory: 13708 grad_norm: 7.2933 loss: 0.9432 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9432 2023/02/18 03:57:16 - mmengine - INFO - Epoch(train) [49][ 40/1320] lr: 2.0000e-04 eta: 0:11:10 time: 0.2587 data_time: 0.0115 memory: 13708 grad_norm: 7.0689 loss: 0.9710 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9710 2023/02/18 03:57:21 - mmengine - INFO - Epoch(train) [49][ 60/1320] lr: 2.0000e-04 eta: 0:11:05 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 7.3051 loss: 0.9248 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9248 2023/02/18 03:57:26 - mmengine - INFO - Epoch(train) [49][ 80/1320] lr: 2.0000e-04 eta: 0:11:00 time: 0.2561 data_time: 0.0110 memory: 13708 grad_norm: 7.0719 loss: 0.9171 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9171 2023/02/18 03:57:31 - mmengine - INFO - Epoch(train) [49][ 100/1320] lr: 2.0000e-04 eta: 0:10:55 time: 0.2556 data_time: 0.0107 memory: 13708 grad_norm: 7.3285 loss: 0.7705 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7705 2023/02/18 03:57:36 - mmengine - INFO - Epoch(train) [49][ 120/1320] lr: 2.0000e-04 eta: 0:10:50 time: 0.2560 data_time: 0.0107 memory: 13708 grad_norm: 7.1762 loss: 0.7928 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7928 2023/02/18 03:57:41 - mmengine - INFO - Epoch(train) [49][ 140/1320] lr: 2.0000e-04 eta: 0:10:45 time: 0.2568 data_time: 0.0109 memory: 13708 grad_norm: 7.2546 loss: 0.8549 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8549 2023/02/18 03:57:47 - mmengine - INFO - Epoch(train) [49][ 160/1320] lr: 2.0000e-04 eta: 0:10:39 time: 0.2561 data_time: 0.0105 memory: 13708 grad_norm: 7.2210 loss: 1.0719 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0719 2023/02/18 03:57:52 - mmengine - INFO - Epoch(train) [49][ 180/1320] lr: 2.0000e-04 eta: 0:10:34 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 7.1865 loss: 0.9793 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9793 2023/02/18 03:57:57 - mmengine - INFO - Epoch(train) [49][ 200/1320] lr: 2.0000e-04 eta: 0:10:29 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 7.2213 loss: 0.8200 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8200 2023/02/18 03:58:02 - mmengine - INFO - Epoch(train) [49][ 220/1320] lr: 2.0000e-04 eta: 0:10:24 time: 0.2579 data_time: 0.0125 memory: 13708 grad_norm: 7.1837 loss: 0.9955 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9955 2023/02/18 03:58:07 - mmengine - INFO - Epoch(train) [49][ 240/1320] lr: 2.0000e-04 eta: 0:10:19 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 7.3950 loss: 0.9764 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9764 2023/02/18 03:58:12 - mmengine - INFO - Epoch(train) [49][ 260/1320] lr: 2.0000e-04 eta: 0:10:14 time: 0.2566 data_time: 0.0109 memory: 13708 grad_norm: 6.9931 loss: 0.8227 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8227 2023/02/18 03:58:17 - mmengine - INFO - Epoch(train) [49][ 280/1320] lr: 2.0000e-04 eta: 0:10:08 time: 0.2566 data_time: 0.0109 memory: 13708 grad_norm: 7.2768 loss: 0.8933 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.8933 2023/02/18 03:58:22 - mmengine - INFO - Epoch(train) [49][ 300/1320] lr: 2.0000e-04 eta: 0:10:03 time: 0.2572 data_time: 0.0117 memory: 13708 grad_norm: 7.2772 loss: 0.8563 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 0.8563 2023/02/18 03:58:28 - mmengine - INFO - Epoch(train) [49][ 320/1320] lr: 2.0000e-04 eta: 0:09:58 time: 0.2563 data_time: 0.0105 memory: 13708 grad_norm: 7.2372 loss: 0.8249 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8249 2023/02/18 03:58:33 - mmengine - INFO - Epoch(train) [49][ 340/1320] lr: 2.0000e-04 eta: 0:09:53 time: 0.2573 data_time: 0.0116 memory: 13708 grad_norm: 7.2249 loss: 1.0241 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0241 2023/02/18 03:58:38 - mmengine - INFO - Epoch(train) [49][ 360/1320] lr: 2.0000e-04 eta: 0:09:48 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 6.9461 loss: 0.8594 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8594 2023/02/18 03:58:43 - mmengine - INFO - Epoch(train) [49][ 380/1320] lr: 2.0000e-04 eta: 0:09:43 time: 0.2577 data_time: 0.0115 memory: 13708 grad_norm: 7.2524 loss: 0.8692 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8692 2023/02/18 03:58:48 - mmengine - INFO - Epoch(train) [49][ 400/1320] lr: 2.0000e-04 eta: 0:09:37 time: 0.2571 data_time: 0.0116 memory: 13708 grad_norm: 7.1488 loss: 0.9785 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9785 2023/02/18 03:58:53 - mmengine - INFO - Epoch(train) [49][ 420/1320] lr: 2.0000e-04 eta: 0:09:32 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 6.9505 loss: 0.8858 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8858 2023/02/18 03:58:58 - mmengine - INFO - Epoch(train) [49][ 440/1320] lr: 2.0000e-04 eta: 0:09:27 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 7.0399 loss: 0.9224 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9224 2023/02/18 03:59:04 - mmengine - INFO - Epoch(train) [49][ 460/1320] lr: 2.0000e-04 eta: 0:09:22 time: 0.2567 data_time: 0.0110 memory: 13708 grad_norm: 7.3270 loss: 0.8880 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.8880 2023/02/18 03:59:09 - mmengine - INFO - Epoch(train) [49][ 480/1320] lr: 2.0000e-04 eta: 0:09:17 time: 0.2557 data_time: 0.0103 memory: 13708 grad_norm: 7.1763 loss: 0.8824 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8824 2023/02/18 03:59:14 - mmengine - INFO - Epoch(train) [49][ 500/1320] lr: 2.0000e-04 eta: 0:09:12 time: 0.2569 data_time: 0.0113 memory: 13708 grad_norm: 7.1579 loss: 1.0127 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0127 2023/02/18 03:59:19 - mmengine - INFO - Epoch(train) [49][ 520/1320] lr: 2.0000e-04 eta: 0:09:06 time: 0.2581 data_time: 0.0128 memory: 13708 grad_norm: 6.9339 loss: 0.9116 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9116 2023/02/18 03:59:24 - mmengine - INFO - Epoch(train) [49][ 540/1320] lr: 2.0000e-04 eta: 0:09:01 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 7.0277 loss: 0.9285 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9285 2023/02/18 03:59:29 - mmengine - INFO - Epoch(train) [49][ 560/1320] lr: 2.0000e-04 eta: 0:08:56 time: 0.2569 data_time: 0.0111 memory: 13708 grad_norm: 7.2188 loss: 0.8595 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8595 2023/02/18 03:59:34 - mmengine - INFO - Epoch(train) [49][ 580/1320] lr: 2.0000e-04 eta: 0:08:51 time: 0.2580 data_time: 0.0127 memory: 13708 grad_norm: 6.9332 loss: 0.8525 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8525 2023/02/18 03:59:40 - mmengine - INFO - Epoch(train) [49][ 600/1320] lr: 2.0000e-04 eta: 0:08:46 time: 0.2561 data_time: 0.0111 memory: 13708 grad_norm: 7.0339 loss: 0.9018 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 0.9018 2023/02/18 03:59:45 - mmengine - INFO - Epoch(train) [49][ 620/1320] lr: 2.0000e-04 eta: 0:08:41 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 7.3499 loss: 0.8915 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 0.8915 2023/02/18 03:59:50 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 03:59:50 - mmengine - INFO - Epoch(train) [49][ 640/1320] lr: 2.0000e-04 eta: 0:08:35 time: 0.2562 data_time: 0.0104 memory: 13708 grad_norm: 7.1304 loss: 0.8931 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8931 2023/02/18 03:59:55 - mmengine - INFO - Epoch(train) [49][ 660/1320] lr: 2.0000e-04 eta: 0:08:30 time: 0.2559 data_time: 0.0110 memory: 13708 grad_norm: 7.1942 loss: 0.8882 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8882 2023/02/18 04:00:00 - mmengine - INFO - Epoch(train) [49][ 680/1320] lr: 2.0000e-04 eta: 0:08:25 time: 0.2567 data_time: 0.0113 memory: 13708 grad_norm: 7.1523 loss: 0.7396 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7396 2023/02/18 04:00:05 - mmengine - INFO - Epoch(train) [49][ 700/1320] lr: 2.0000e-04 eta: 0:08:20 time: 0.2557 data_time: 0.0107 memory: 13708 grad_norm: 7.3913 loss: 1.0721 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0721 2023/02/18 04:00:10 - mmengine - INFO - Epoch(train) [49][ 720/1320] lr: 2.0000e-04 eta: 0:08:15 time: 0.2571 data_time: 0.0108 memory: 13708 grad_norm: 7.0608 loss: 0.8460 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8460 2023/02/18 04:00:15 - mmengine - INFO - Epoch(train) [49][ 740/1320] lr: 2.0000e-04 eta: 0:08:10 time: 0.2560 data_time: 0.0110 memory: 13708 grad_norm: 6.9977 loss: 0.9411 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9411 2023/02/18 04:00:21 - mmengine - INFO - Epoch(train) [49][ 760/1320] lr: 2.0000e-04 eta: 0:08:05 time: 0.2563 data_time: 0.0108 memory: 13708 grad_norm: 7.2824 loss: 0.9132 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9132 2023/02/18 04:00:26 - mmengine - INFO - Epoch(train) [49][ 780/1320] lr: 2.0000e-04 eta: 0:07:59 time: 0.2560 data_time: 0.0108 memory: 13708 grad_norm: 6.9796 loss: 0.8671 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8671 2023/02/18 04:00:31 - mmengine - INFO - Epoch(train) [49][ 800/1320] lr: 2.0000e-04 eta: 0:07:54 time: 0.2562 data_time: 0.0107 memory: 13708 grad_norm: 7.1251 loss: 0.9067 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9067 2023/02/18 04:00:36 - mmengine - INFO - Epoch(train) [49][ 820/1320] lr: 2.0000e-04 eta: 0:07:49 time: 0.2566 data_time: 0.0108 memory: 13708 grad_norm: 7.1372 loss: 0.7861 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7861 2023/02/18 04:00:41 - mmengine - INFO - Epoch(train) [49][ 840/1320] lr: 2.0000e-04 eta: 0:07:44 time: 0.2573 data_time: 0.0111 memory: 13708 grad_norm: 7.1083 loss: 0.9290 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9290 2023/02/18 04:00:46 - mmengine - INFO - Epoch(train) [49][ 860/1320] lr: 2.0000e-04 eta: 0:07:39 time: 0.2562 data_time: 0.0112 memory: 13708 grad_norm: 6.9915 loss: 0.7754 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.7754 2023/02/18 04:00:51 - mmengine - INFO - Epoch(train) [49][ 880/1320] lr: 2.0000e-04 eta: 0:07:34 time: 0.2568 data_time: 0.0111 memory: 13708 grad_norm: 7.3165 loss: 0.8748 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8748 2023/02/18 04:00:57 - mmengine - INFO - Epoch(train) [49][ 900/1320] lr: 2.0000e-04 eta: 0:07:28 time: 0.2568 data_time: 0.0109 memory: 13708 grad_norm: 7.0622 loss: 0.8405 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8405 2023/02/18 04:01:02 - mmengine - INFO - Epoch(train) [49][ 920/1320] lr: 2.0000e-04 eta: 0:07:23 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 7.5456 loss: 0.8478 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8478 2023/02/18 04:01:07 - mmengine - INFO - Epoch(train) [49][ 940/1320] lr: 2.0000e-04 eta: 0:07:18 time: 0.2562 data_time: 0.0110 memory: 13708 grad_norm: 7.1526 loss: 0.9465 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 0.9465 2023/02/18 04:01:12 - mmengine - INFO - Epoch(train) [49][ 960/1320] lr: 2.0000e-04 eta: 0:07:13 time: 0.2570 data_time: 0.0108 memory: 13708 grad_norm: 7.1426 loss: 0.8653 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.8653 2023/02/18 04:01:17 - mmengine - INFO - Epoch(train) [49][ 980/1320] lr: 2.0000e-04 eta: 0:07:08 time: 0.2570 data_time: 0.0117 memory: 13708 grad_norm: 7.1338 loss: 0.8773 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8773 2023/02/18 04:01:22 - mmengine - INFO - Epoch(train) [49][1000/1320] lr: 2.0000e-04 eta: 0:07:03 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 7.3397 loss: 1.0108 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0108 2023/02/18 04:01:27 - mmengine - INFO - Epoch(train) [49][1020/1320] lr: 2.0000e-04 eta: 0:06:57 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 7.4154 loss: 0.8730 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8730 2023/02/18 04:01:33 - mmengine - INFO - Epoch(train) [49][1040/1320] lr: 2.0000e-04 eta: 0:06:52 time: 0.2567 data_time: 0.0112 memory: 13708 grad_norm: 7.4508 loss: 0.9736 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9736 2023/02/18 04:01:38 - mmengine - INFO - Epoch(train) [49][1060/1320] lr: 2.0000e-04 eta: 0:06:47 time: 0.2567 data_time: 0.0111 memory: 13708 grad_norm: 7.2434 loss: 0.8644 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8644 2023/02/18 04:01:43 - mmengine - INFO - Epoch(train) [49][1080/1320] lr: 2.0000e-04 eta: 0:06:42 time: 0.2573 data_time: 0.0122 memory: 13708 grad_norm: 7.1904 loss: 0.9277 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9277 2023/02/18 04:01:48 - mmengine - INFO - Epoch(train) [49][1100/1320] lr: 2.0000e-04 eta: 0:06:37 time: 0.2565 data_time: 0.0112 memory: 13708 grad_norm: 7.1077 loss: 0.9439 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9439 2023/02/18 04:01:53 - mmengine - INFO - Epoch(train) [49][1120/1320] lr: 2.0000e-04 eta: 0:06:32 time: 0.2570 data_time: 0.0114 memory: 13708 grad_norm: 7.3362 loss: 0.8987 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8987 2023/02/18 04:01:58 - mmengine - INFO - Epoch(train) [49][1140/1320] lr: 2.0000e-04 eta: 0:06:26 time: 0.2572 data_time: 0.0109 memory: 13708 grad_norm: 7.4312 loss: 0.9412 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9412 2023/02/18 04:02:03 - mmengine - INFO - Epoch(train) [49][1160/1320] lr: 2.0000e-04 eta: 0:06:21 time: 0.2586 data_time: 0.0130 memory: 13708 grad_norm: 7.3025 loss: 1.1226 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1226 2023/02/18 04:02:09 - mmengine - INFO - Epoch(train) [49][1180/1320] lr: 2.0000e-04 eta: 0:06:16 time: 0.2565 data_time: 0.0107 memory: 13708 grad_norm: 7.0953 loss: 0.6602 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.6602 2023/02/18 04:02:14 - mmengine - INFO - Epoch(train) [49][1200/1320] lr: 2.0000e-04 eta: 0:06:11 time: 0.2572 data_time: 0.0110 memory: 13708 grad_norm: 7.1389 loss: 0.9088 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9088 2023/02/18 04:02:19 - mmengine - INFO - Epoch(train) [49][1220/1320] lr: 2.0000e-04 eta: 0:06:06 time: 0.2562 data_time: 0.0113 memory: 13708 grad_norm: 7.3727 loss: 1.0824 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0824 2023/02/18 04:02:24 - mmengine - INFO - Epoch(train) [49][1240/1320] lr: 2.0000e-04 eta: 0:06:01 time: 0.2558 data_time: 0.0108 memory: 13708 grad_norm: 7.3865 loss: 0.9292 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9292 2023/02/18 04:02:29 - mmengine - INFO - Epoch(train) [49][1260/1320] lr: 2.0000e-04 eta: 0:05:56 time: 0.2572 data_time: 0.0108 memory: 13708 grad_norm: 7.1733 loss: 0.9345 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9345 2023/02/18 04:02:34 - mmengine - INFO - Epoch(train) [49][1280/1320] lr: 2.0000e-04 eta: 0:05:50 time: 0.2567 data_time: 0.0107 memory: 13708 grad_norm: 7.1638 loss: 0.8941 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8941 2023/02/18 04:02:39 - mmengine - INFO - Epoch(train) [49][1300/1320] lr: 2.0000e-04 eta: 0:05:45 time: 0.2564 data_time: 0.0110 memory: 13708 grad_norm: 7.2478 loss: 0.9059 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9059 2023/02/18 04:02:44 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 04:02:44 - mmengine - INFO - Epoch(train) [49][1320/1320] lr: 2.0000e-04 eta: 0:05:40 time: 0.2520 data_time: 0.0108 memory: 13708 grad_norm: 7.1707 loss: 0.8786 top1_acc: 0.9091 top5_acc: 1.0000 loss_cls: 0.8786 2023/02/18 04:02:47 - mmengine - INFO - Epoch(val) [49][ 20/194] eta: 0:00:21 time: 0.1226 data_time: 0.0543 memory: 1818 2023/02/18 04:02:49 - mmengine - INFO - Epoch(val) [49][ 40/194] eta: 0:00:16 time: 0.0885 data_time: 0.0206 memory: 1818 2023/02/18 04:02:51 - mmengine - INFO - Epoch(val) [49][ 60/194] eta: 0:00:13 time: 0.0951 data_time: 0.0264 memory: 1818 2023/02/18 04:02:52 - mmengine - INFO - Epoch(val) [49][ 80/194] eta: 0:00:11 time: 0.0847 data_time: 0.0162 memory: 1818 2023/02/18 04:02:54 - mmengine - INFO - Epoch(val) [49][100/194] eta: 0:00:09 time: 0.0914 data_time: 0.0232 memory: 1818 2023/02/18 04:02:56 - mmengine - INFO - Epoch(val) [49][120/194] eta: 0:00:07 time: 0.0859 data_time: 0.0181 memory: 1818 2023/02/18 04:02:58 - mmengine - INFO - Epoch(val) [49][140/194] eta: 0:00:05 time: 0.0931 data_time: 0.0252 memory: 1818 2023/02/18 04:02:59 - mmengine - INFO - Epoch(val) [49][160/194] eta: 0:00:03 time: 0.0797 data_time: 0.0121 memory: 1818 2023/02/18 04:03:01 - mmengine - INFO - Epoch(val) [49][180/194] eta: 0:00:01 time: 0.0852 data_time: 0.0174 memory: 1818 2023/02/18 04:03:03 - mmengine - INFO - Epoch(val) [49][194/194] acc/top1: 0.5980 acc/top5: 0.8624 acc/mean1: 0.5337 2023/02/18 04:03:03 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb.py/best_acc/top1_epoch_48.pth is removed 2023/02/18 04:03:04 - mmengine - INFO - The best checkpoint with 0.5980 acc/top1 at 49 epoch is saved to best_acc/top1_epoch_49.pth. 2023/02/18 04:03:10 - mmengine - INFO - Epoch(train) [50][ 20/1320] lr: 2.0000e-04 eta: 0:05:35 time: 0.2971 data_time: 0.0429 memory: 13708 grad_norm: 7.2995 loss: 0.8499 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8499 2023/02/18 04:03:15 - mmengine - INFO - Epoch(train) [50][ 40/1320] lr: 2.0000e-04 eta: 0:05:30 time: 0.2582 data_time: 0.0115 memory: 13708 grad_norm: 7.3194 loss: 1.0056 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0056 2023/02/18 04:03:20 - mmengine - INFO - Epoch(train) [50][ 60/1320] lr: 2.0000e-04 eta: 0:05:25 time: 0.2568 data_time: 0.0108 memory: 13708 grad_norm: 7.2190 loss: 0.8713 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8713 2023/02/18 04:03:25 - mmengine - INFO - Epoch(train) [50][ 80/1320] lr: 2.0000e-04 eta: 0:05:19 time: 0.2563 data_time: 0.0106 memory: 13708 grad_norm: 7.0336 loss: 0.9113 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9113 2023/02/18 04:03:30 - mmengine - INFO - Epoch(train) [50][ 100/1320] lr: 2.0000e-04 eta: 0:05:14 time: 0.2560 data_time: 0.0103 memory: 13708 grad_norm: 7.3561 loss: 0.9927 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9927 2023/02/18 04:03:36 - mmengine - INFO - Epoch(train) [50][ 120/1320] lr: 2.0000e-04 eta: 0:05:09 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 7.2880 loss: 0.7813 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7813 2023/02/18 04:03:41 - mmengine - INFO - Epoch(train) [50][ 140/1320] lr: 2.0000e-04 eta: 0:05:04 time: 0.2562 data_time: 0.0103 memory: 13708 grad_norm: 7.2423 loss: 0.8783 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8783 2023/02/18 04:03:46 - mmengine - INFO - Epoch(train) [50][ 160/1320] lr: 2.0000e-04 eta: 0:04:59 time: 0.2566 data_time: 0.0106 memory: 13708 grad_norm: 7.1350 loss: 0.9616 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 0.9616 2023/02/18 04:03:51 - mmengine - INFO - Epoch(train) [50][ 180/1320] lr: 2.0000e-04 eta: 0:04:54 time: 0.2563 data_time: 0.0114 memory: 13708 grad_norm: 7.2408 loss: 0.8825 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8825 2023/02/18 04:03:56 - mmengine - INFO - Epoch(train) [50][ 200/1320] lr: 2.0000e-04 eta: 0:04:48 time: 0.2565 data_time: 0.0110 memory: 13708 grad_norm: 7.2885 loss: 0.8584 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8584 2023/02/18 04:04:01 - mmengine - INFO - Epoch(train) [50][ 220/1320] lr: 2.0000e-04 eta: 0:04:43 time: 0.2558 data_time: 0.0109 memory: 13708 grad_norm: 7.2192 loss: 0.8481 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.8481 2023/02/18 04:04:06 - mmengine - INFO - Epoch(train) [50][ 240/1320] lr: 2.0000e-04 eta: 0:04:38 time: 0.2563 data_time: 0.0112 memory: 13708 grad_norm: 7.2393 loss: 1.0555 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0555 2023/02/18 04:04:12 - mmengine - INFO - Epoch(train) [50][ 260/1320] lr: 2.0000e-04 eta: 0:04:33 time: 0.2566 data_time: 0.0113 memory: 13708 grad_norm: 7.2509 loss: 0.8461 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.8461 2023/02/18 04:04:17 - mmengine - INFO - Epoch(train) [50][ 280/1320] lr: 2.0000e-04 eta: 0:04:28 time: 0.2571 data_time: 0.0110 memory: 13708 grad_norm: 7.2681 loss: 0.8568 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8568 2023/02/18 04:04:22 - mmengine - INFO - Epoch(train) [50][ 300/1320] lr: 2.0000e-04 eta: 0:04:23 time: 0.2576 data_time: 0.0118 memory: 13708 grad_norm: 7.2620 loss: 0.8252 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.8252 2023/02/18 04:04:27 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 04:04:27 - mmengine - INFO - Epoch(train) [50][ 320/1320] lr: 2.0000e-04 eta: 0:04:17 time: 0.2568 data_time: 0.0109 memory: 13708 grad_norm: 7.2424 loss: 0.8733 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8733 2023/02/18 04:04:32 - mmengine - INFO - Epoch(train) [50][ 340/1320] lr: 2.0000e-04 eta: 0:04:12 time: 0.2558 data_time: 0.0107 memory: 13708 grad_norm: 7.1515 loss: 0.8774 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8774 2023/02/18 04:04:37 - mmengine - INFO - Epoch(train) [50][ 360/1320] lr: 2.0000e-04 eta: 0:04:07 time: 0.2584 data_time: 0.0122 memory: 13708 grad_norm: 7.1707 loss: 0.9823 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9823 2023/02/18 04:04:42 - mmengine - INFO - Epoch(train) [50][ 380/1320] lr: 2.0000e-04 eta: 0:04:02 time: 0.2569 data_time: 0.0109 memory: 13708 grad_norm: 7.2965 loss: 0.9232 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 0.9232 2023/02/18 04:04:48 - mmengine - INFO - Epoch(train) [50][ 400/1320] lr: 2.0000e-04 eta: 0:03:57 time: 0.2562 data_time: 0.0112 memory: 13708 grad_norm: 7.3283 loss: 0.9607 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9607 2023/02/18 04:04:53 - mmengine - INFO - Epoch(train) [50][ 420/1320] lr: 2.0000e-04 eta: 0:03:52 time: 0.2570 data_time: 0.0108 memory: 13708 grad_norm: 7.3526 loss: 0.7417 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7417 2023/02/18 04:04:58 - mmengine - INFO - Epoch(train) [50][ 440/1320] lr: 2.0000e-04 eta: 0:03:47 time: 0.2569 data_time: 0.0113 memory: 13708 grad_norm: 7.2919 loss: 0.8851 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.8851 2023/02/18 04:05:03 - mmengine - INFO - Epoch(train) [50][ 460/1320] lr: 2.0000e-04 eta: 0:03:41 time: 0.2564 data_time: 0.0110 memory: 13708 grad_norm: 7.1217 loss: 1.0150 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0150 2023/02/18 04:05:08 - mmengine - INFO - Epoch(train) [50][ 480/1320] lr: 2.0000e-04 eta: 0:03:36 time: 0.2567 data_time: 0.0112 memory: 13708 grad_norm: 7.1819 loss: 0.9514 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9514 2023/02/18 04:05:13 - mmengine - INFO - Epoch(train) [50][ 500/1320] lr: 2.0000e-04 eta: 0:03:31 time: 0.2564 data_time: 0.0108 memory: 13708 grad_norm: 7.1672 loss: 0.8183 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8183 2023/02/18 04:05:18 - mmengine - INFO - Epoch(train) [50][ 520/1320] lr: 2.0000e-04 eta: 0:03:26 time: 0.2561 data_time: 0.0109 memory: 13708 grad_norm: 7.0952 loss: 0.9791 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9791 2023/02/18 04:05:23 - mmengine - INFO - Epoch(train) [50][ 540/1320] lr: 2.0000e-04 eta: 0:03:21 time: 0.2563 data_time: 0.0111 memory: 13708 grad_norm: 7.3204 loss: 0.9860 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9860 2023/02/18 04:05:29 - mmengine - INFO - Epoch(train) [50][ 560/1320] lr: 2.0000e-04 eta: 0:03:16 time: 0.2564 data_time: 0.0109 memory: 13708 grad_norm: 7.1019 loss: 0.9215 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 0.9215 2023/02/18 04:05:34 - mmengine - INFO - Epoch(train) [50][ 580/1320] lr: 2.0000e-04 eta: 0:03:10 time: 0.2574 data_time: 0.0108 memory: 13708 grad_norm: 7.2317 loss: 0.8022 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8022 2023/02/18 04:05:39 - mmengine - INFO - Epoch(train) [50][ 600/1320] lr: 2.0000e-04 eta: 0:03:05 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 7.3129 loss: 0.9024 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.9024 2023/02/18 04:05:44 - mmengine - INFO - Epoch(train) [50][ 620/1320] lr: 2.0000e-04 eta: 0:03:00 time: 0.2575 data_time: 0.0115 memory: 13708 grad_norm: 7.3637 loss: 0.8574 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8574 2023/02/18 04:05:49 - mmengine - INFO - Epoch(train) [50][ 640/1320] lr: 2.0000e-04 eta: 0:02:55 time: 0.2572 data_time: 0.0108 memory: 13708 grad_norm: 7.4235 loss: 1.0699 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0699 2023/02/18 04:05:54 - mmengine - INFO - Epoch(train) [50][ 660/1320] lr: 2.0000e-04 eta: 0:02:50 time: 0.2563 data_time: 0.0107 memory: 13708 grad_norm: 7.0846 loss: 0.9053 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.9053 2023/02/18 04:05:59 - mmengine - INFO - Epoch(train) [50][ 680/1320] lr: 2.0000e-04 eta: 0:02:45 time: 0.2563 data_time: 0.0110 memory: 13708 grad_norm: 7.3861 loss: 0.8590 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8590 2023/02/18 04:06:05 - mmengine - INFO - Epoch(train) [50][ 700/1320] lr: 2.0000e-04 eta: 0:02:39 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 7.2401 loss: 0.8772 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8772 2023/02/18 04:06:10 - mmengine - INFO - Epoch(train) [50][ 720/1320] lr: 2.0000e-04 eta: 0:02:34 time: 0.2566 data_time: 0.0111 memory: 13708 grad_norm: 7.4199 loss: 0.9128 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9128 2023/02/18 04:06:15 - mmengine - INFO - Epoch(train) [50][ 740/1320] lr: 2.0000e-04 eta: 0:02:29 time: 0.2565 data_time: 0.0108 memory: 13708 grad_norm: 7.2042 loss: 0.9777 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9777 2023/02/18 04:06:20 - mmengine - INFO - Epoch(train) [50][ 760/1320] lr: 2.0000e-04 eta: 0:02:24 time: 0.2562 data_time: 0.0115 memory: 13708 grad_norm: 7.2940 loss: 0.9162 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9162 2023/02/18 04:06:25 - mmengine - INFO - Epoch(train) [50][ 780/1320] lr: 2.0000e-04 eta: 0:02:19 time: 0.2569 data_time: 0.0111 memory: 13708 grad_norm: 7.3780 loss: 1.0471 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0471 2023/02/18 04:06:30 - mmengine - INFO - Epoch(train) [50][ 800/1320] lr: 2.0000e-04 eta: 0:02:14 time: 0.2570 data_time: 0.0109 memory: 13708 grad_norm: 7.4050 loss: 0.8456 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8456 2023/02/18 04:06:35 - mmengine - INFO - Epoch(train) [50][ 820/1320] lr: 2.0000e-04 eta: 0:02:08 time: 0.2573 data_time: 0.0110 memory: 13708 grad_norm: 7.3134 loss: 0.9435 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9435 2023/02/18 04:06:41 - mmengine - INFO - Epoch(train) [50][ 840/1320] lr: 2.0000e-04 eta: 0:02:03 time: 0.2567 data_time: 0.0112 memory: 13708 grad_norm: 7.2425 loss: 0.8200 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.8200 2023/02/18 04:06:46 - mmengine - INFO - Epoch(train) [50][ 860/1320] lr: 2.0000e-04 eta: 0:01:58 time: 0.2565 data_time: 0.0109 memory: 13708 grad_norm: 6.9564 loss: 0.7982 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7982 2023/02/18 04:06:51 - mmengine - INFO - Epoch(train) [50][ 880/1320] lr: 2.0000e-04 eta: 0:01:53 time: 0.2562 data_time: 0.0108 memory: 13708 grad_norm: 7.1298 loss: 0.7339 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 0.7339 2023/02/18 04:06:56 - mmengine - INFO - Epoch(train) [50][ 900/1320] lr: 2.0000e-04 eta: 0:01:48 time: 0.2570 data_time: 0.0118 memory: 13708 grad_norm: 7.1877 loss: 0.9823 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9823 2023/02/18 04:07:01 - mmengine - INFO - Epoch(train) [50][ 920/1320] lr: 2.0000e-04 eta: 0:01:43 time: 0.2561 data_time: 0.0107 memory: 13708 grad_norm: 7.3736 loss: 0.8746 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.8746 2023/02/18 04:07:06 - mmengine - INFO - Epoch(train) [50][ 940/1320] lr: 2.0000e-04 eta: 0:01:38 time: 0.2564 data_time: 0.0110 memory: 13708 grad_norm: 7.4643 loss: 0.9070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.9070 2023/02/18 04:07:11 - mmengine - INFO - Epoch(train) [50][ 960/1320] lr: 2.0000e-04 eta: 0:01:32 time: 0.2569 data_time: 0.0112 memory: 13708 grad_norm: 7.4277 loss: 0.9964 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9964 2023/02/18 04:07:17 - mmengine - INFO - Epoch(train) [50][ 980/1320] lr: 2.0000e-04 eta: 0:01:27 time: 0.2561 data_time: 0.0104 memory: 13708 grad_norm: 7.2251 loss: 0.8795 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.8795 2023/02/18 04:07:22 - mmengine - INFO - Epoch(train) [50][1000/1320] lr: 2.0000e-04 eta: 0:01:22 time: 0.2564 data_time: 0.0111 memory: 13708 grad_norm: 7.5155 loss: 1.0620 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.0620 2023/02/18 04:07:27 - mmengine - INFO - Epoch(train) [50][1020/1320] lr: 2.0000e-04 eta: 0:01:17 time: 0.2568 data_time: 0.0103 memory: 13708 grad_norm: 7.2194 loss: 1.0353 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0353 2023/02/18 04:07:32 - mmengine - INFO - Epoch(train) [50][1040/1320] lr: 2.0000e-04 eta: 0:01:12 time: 0.2568 data_time: 0.0111 memory: 13708 grad_norm: 7.1137 loss: 0.8593 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8593 2023/02/18 04:07:37 - mmengine - INFO - Epoch(train) [50][1060/1320] lr: 2.0000e-04 eta: 0:01:07 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 7.1411 loss: 0.8857 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8857 2023/02/18 04:07:42 - mmengine - INFO - Epoch(train) [50][1080/1320] lr: 2.0000e-04 eta: 0:01:01 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 7.2084 loss: 0.9009 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9009 2023/02/18 04:07:47 - mmengine - INFO - Epoch(train) [50][1100/1320] lr: 2.0000e-04 eta: 0:00:56 time: 0.2566 data_time: 0.0108 memory: 13708 grad_norm: 7.4285 loss: 0.8926 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8926 2023/02/18 04:07:52 - mmengine - INFO - Epoch(train) [50][1120/1320] lr: 2.0000e-04 eta: 0:00:51 time: 0.2571 data_time: 0.0120 memory: 13708 grad_norm: 7.1963 loss: 0.8182 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8182 2023/02/18 04:07:58 - mmengine - INFO - Epoch(train) [50][1140/1320] lr: 2.0000e-04 eta: 0:00:46 time: 0.2561 data_time: 0.0106 memory: 13708 grad_norm: 7.3785 loss: 0.7579 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7579 2023/02/18 04:08:03 - mmengine - INFO - Epoch(train) [50][1160/1320] lr: 2.0000e-04 eta: 0:00:41 time: 0.2565 data_time: 0.0106 memory: 13708 grad_norm: 7.3581 loss: 0.7675 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7675 2023/02/18 04:09:43 - mmengine - INFO - Epoch(train) [50][1180/1320] lr: 2.0000e-04 eta: 0:00:36 time: 5.0342 data_time: 0.0106 memory: 13708 grad_norm: 7.0613 loss: 0.8361 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8361 2023/02/18 04:09:49 - mmengine - INFO - Epoch(train) [50][1200/1320] lr: 2.0000e-04 eta: 0:00:31 time: 0.2567 data_time: 0.0109 memory: 13708 grad_norm: 7.3279 loss: 0.7968 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7968 2023/02/18 04:09:54 - mmengine - INFO - Epoch(train) [50][1220/1320] lr: 2.0000e-04 eta: 0:00:25 time: 0.2562 data_time: 0.0111 memory: 13708 grad_norm: 7.4351 loss: 0.7709 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.7709 2023/02/18 04:09:59 - mmengine - INFO - Epoch(train) [50][1240/1320] lr: 2.0000e-04 eta: 0:00:20 time: 0.2562 data_time: 0.0109 memory: 13708 grad_norm: 7.2377 loss: 0.8231 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8231 2023/02/18 04:10:04 - mmengine - INFO - Epoch(train) [50][1260/1320] lr: 2.0000e-04 eta: 0:00:15 time: 0.2566 data_time: 0.0108 memory: 13708 grad_norm: 7.1521 loss: 0.8973 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8973 2023/02/18 04:10:09 - mmengine - INFO - Epoch(train) [50][1280/1320] lr: 2.0000e-04 eta: 0:00:10 time: 0.2575 data_time: 0.0121 memory: 13708 grad_norm: 7.1321 loss: 0.8702 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8702 2023/02/18 04:10:14 - mmengine - INFO - Epoch(train) [50][1300/1320] lr: 2.0000e-04 eta: 0:00:05 time: 0.2560 data_time: 0.0109 memory: 13708 grad_norm: 7.3606 loss: 0.8379 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8379 2023/02/18 04:10:19 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x8-50e_sthv2-rgb_20230217_230810 2023/02/18 04:10:19 - mmengine - INFO - Epoch(train) [50][1320/1320] lr: 2.0000e-04 eta: 0:00:00 time: 0.2533 data_time: 0.0107 memory: 13708 grad_norm: 7.2661 loss: 0.7908 top1_acc: 0.8182 top5_acc: 0.9091 loss_cls: 0.7908 2023/02/18 04:10:19 - mmengine - INFO - Saving checkpoint at 50 epochs 2023/02/18 04:10:23 - mmengine - INFO - Epoch(val) [50][ 20/194] eta: 0:00:21 time: 0.1256 data_time: 0.0562 memory: 1818 2023/02/18 04:10:25 - mmengine - INFO - Epoch(val) [50][ 40/194] eta: 0:00:16 time: 0.0925 data_time: 0.0248 memory: 1818 2023/02/18 04:10:27 - mmengine - INFO - Epoch(val) [50][ 60/194] eta: 0:00:13 time: 0.0888 data_time: 0.0206 memory: 1818 2023/02/18 04:10:28 - mmengine - INFO - Epoch(val) [50][ 80/194] eta: 0:00:11 time: 0.0851 data_time: 0.0166 memory: 1818 2023/02/18 04:10:30 - mmengine - INFO - Epoch(val) [50][100/194] eta: 0:00:09 time: 0.0897 data_time: 0.0215 memory: 1818 2023/02/18 04:10:32 - mmengine - INFO - Epoch(val) [50][120/194] eta: 0:00:07 time: 0.0926 data_time: 0.0249 memory: 1818 2023/02/18 04:10:34 - mmengine - INFO - Epoch(val) [50][140/194] eta: 0:00:05 time: 0.0848 data_time: 0.0159 memory: 1818 2023/02/18 04:10:35 - mmengine - INFO - Epoch(val) [50][160/194] eta: 0:00:03 time: 0.0810 data_time: 0.0129 memory: 1818 2023/02/18 04:10:37 - mmengine - INFO - Epoch(val) [50][180/194] eta: 0:00:01 time: 0.0798 data_time: 0.0133 memory: 1818 2023/02/18 04:10:39 - mmengine - INFO - Epoch(val) [50][194/194] acc/top1: 0.5979 acc/top5: 0.8611 acc/mean1: 0.5339